Sampling procedures for inspection by attributes Part 11: Procedures for assessment of declared quality levels for small population
Some standard content:
Is 03. 120.30
National Standard of the People's Republic of China
GB/T2828.11—2008
Replaces GB/T15482—1995
Sampling procedures for inspection hyattrilautes-Part 11: Procedures for assessment of declared quality levels for small populations
Sampling procedures for inspection hyattrilautes-Part 11: Procedures for assessment of declared quality levels for small populations2008-07-16Promulgated
General Administration of Quality Supervision, Inspection and Quarantine of the People's Republic of China and Administration Commission of Standardization of the People's Republic of China
Implemented on 2009-01-01
GB/T 2828. 11—2008
2 Normative references
3 Terms, definitions, symbols and abbreviations
3.1 Terms and definitions
3.2 Symbols and abbreviations
4 Principles
Claim quality level
Implementation procedures for checking oil samples
Determine the overall inspection
Determine the technical performance, quality characteristics and requirements of the unit productDetermine the classification of non-conforming products
Specify and determine the market quality level|| tt||Specify the inspection level
Search the sampling plan
Take the sample
Inspection sample
Disposal of non-conforming products
Judgment rule
Statistical interpretation of sampling theory
Re-inspection and re-test-
6.13 Judge by actual quality level
7 Sampling characteristic function and inspection power of sampling plan 8 Example
Appendix A (Normative Appendix)
Declared quality level LQ1. Appendix (Normative Appendix)
Appendix C (Informative Appendix)
Sampling method index table
Relationship between this part and other parts of GB/T 2628 Appendix D (Informative Appendix)
Sampling inspection function table
GB/T 2828. 11—2008
GB/T 2828 "Sampling inspection procedure for attributes" is divided into the following parts. Its expected structure and corresponding international standards and national standards to be replaced are:
Part 1: Sampling plan for batch inspection according to acceptance quality limit (AQL) inspection case (ISO 2859-1: 1999, II)T: Replaces GB/1 2828—1987>
Part 2: Sampling plan for isolated batch inspection based on limit quality limit (1.Q) (ISO28592:1985, NEQ; replaces GB/T 152351991)
--Part 3: Procedure for skipping batches (ISO2859-3:2005JDT; replaces G13/T132631991)--Part 4: Procedure for assessing the quality level of jH (ISO2859-4:2002, MOD; replaces GB/T144371997 and G :41621993)
Part 5: Sequential sampling system for batch inspection according to acceptance quality limit (AQL) (corresponding to IS028595:2005)...-Part 10: Introduction to attribute sampling system (corresponding to I502859-10:2006). Part 11: Procedure for assessment of small total quality level (replaces CB/T15482-1995) This part is Part 11 of (I3/1 2828). This Part replaces GB/T15182-1995 "Product Quality Supervision Small Population Count-Sub-Sampling Inspection Procedure and Sampling Table". Compared with GB/T15482-1995, this Part has the following technical changes: Change the designated quality level (DQL) to designated quality level (DQL); change the supervision population to the verification population; change the number of non-conforming products to the limit number; change the number of non-conforming monitoring population to the verification population non-conforming; change the number of passed supervision sampling inspection to the verification pass; change the number of qualified random inspection to the number of sample inspection meeting the requirements; add the discussion of comparing the actual quality level with the designated quality level for judgment; add the definition of the effectiveness of re-inspection, re-check and verification sampling inspection; and especially emphasize that this Part In addition to being applicable to final products, parts and components, it can also be used for dyeing, work-in-progress, inventory, and maintenance operations. Data or records, management procedures: individual sampling plans have been adjusted;
Added "Appendix A,
Appendix A and Appendix B of this part are normative appendices, and Appendix D is a record of porcelain material properties. This part was proposed by the China National Institute of Standardization and issued by the National Statistical Technical Committee for the Promotion of Standardization: Drafting units of this part: Wuxi Product Quality Supervision and Inspection Institute, China National Chemical Research Institute, Guangdong Industrial and Commercial Bank Reform and Management Bureau, People's Liberation Army Engineering College, Institute of Mathematics and Systems Science, Chinese Academy of Sciences. Drafters of this part: Chen Huaying, Yu Zhenfan, Guo Zhanqiang, Jianguo, Wenxing, Zhang Yuzhu, and Feng Shiyong. The previous versions of the standard replaced by this part are as follows: - GB/T15182—1995
GB/T 2828.11—2008
GB/T 2828.11 The scope of application of Part 11 of GB/T 2828 is different from Part 1 of GB/T 2828 and Part 4 of GB/T 2828: The system of acceptance sampling procedures specified in Part 1 of GB/T 2828 is applicable to bilateral cooperation between two related parties (such as suppliers and users). Acceptance sampling procedures are practical rules for the delivery of products after a sample of the acceptance batch is used: therefore, these procedures do not involve any formal claimed quality level. In acceptance sampling, it is considered that there is no obvious difference between the quality level of acceptable batches and unacceptable batches. The transfer rules and sampling plan design in GB/T 2828.1 are designed to encourage suppliers to produce products with a process average quality level that is better than the selected AQL. The procedures in Part 1 and Part 3 of GB/T 2828 are applicable to acceptance sampling, but not to verifying the claimed quality of a certain verification population in review and verification. The main reason is that Part 1 and Part 3 of GB/T 2828 are verified by acceptance quality limits, which are only related to the actual purpose of acceptance sampling. Part 11 of GB/T 2828 and Part 4 of GB/T 2828 are both used to evaluate whether the quality level of the verification population does not meet its claimed quality level. However, Part 4 of GB/T 2828 is used for verification of a population exceeding 250. This is because Part 4 of GB/T 2828 uses binomial distribution to calculate the probability of random inspection samples meeting the requirements (cL); while Part 11 of GB/T 2828 is used for verification of a population less than 250. In the case of piece inspection, the probability of the inspection sample meeting the requirement (dL) is calculated. When the inspection is done by piece, if the total number of the inspection population is greater than 250 and the ratio of the batch to the sample is greater than 10, the search sampling plan of GB/T2828.1 shall be used. When the total number of the inspection population is not greater than 250, the search sampling plan of this part shall be used. The sample inspection procedures specified in this part are developed for the sampling inspection required in the evaluation of the specification. When implementing this special form of inspection, the responsible department must consider the risk of making incorrect conclusions and consider the risk in arranging and performing the review (or official review, or test). This part designs some rules so that when the actual quality level of the inspection population actually meets the claimed quality level, the risk of judging the inspection population as unqualified is very small. If it is also hoped that when the actual quality level of the inspection population does not meet the claimed quality level, the risk of judging the inspection as unqualified is also very small, more detailed standards must be considered. In order to minimize the sample size: when the actual quality level does not meet the claimed quality level, the risk of judging the inspection as passed is slightly higher. The difference in judgment results reflects the imbalance of the risk of making different wrong conclusions. When the sampling results judge the inspection population as unqualified, there is a high degree of confidence that "the actual quality level of the inspection population is inferior to the claimed quality level". When the sampling results judge the inspection as passed, it is considered that "for this limited sample size, it is not found that the actual quality level of the inspection population is inferior to the claimed quality level". Therefore, when the sample size is small, the responsible department does not have the responsibility to confirm that the inspection population is qualified for the situation that has been judged. 1 Standard
Sampling inspection procedures for attributes
Part 11 Procedures for assessing the claimed quality level of a small population
GB/I 2828.112008
GB/T2828 This part specifies the counting sampling plan and assessment procedure for assessing whether the quality level of a population (batch or process) does not conform to a certain quality level.
(GB13/T2828 This part is applicable to the small population counting sampling inspection that can take a random sample of some unit products from the inspection population and take the number of unqualified products as the quality indicator. It can be used for various forms of quality inspection, but cannot be used for batch acceptance sampling. The sampling plan provided in this part of GB/T2828 can be used for (but not limited to) the inspection of the following products, such as: - Final product;
- Parts and raw materials
Operation,
- Work in progress;
- Inventory;
- Maintenance work;
- Numbers or records,
Management procedures.
This part is used to divide the inspected unit products into qualified products and unqualified products, and to check the number of unqualified products in the total.
2 Normative references
The clauses in the following documents shall become the clauses of this part through the use of the number of this part of (3/T2828). For all referenced documents with sufficient dates, their accompanying All subsequent amendments (excluding errors) or revisions are not applicable to this part. However, parties to an agreement based on this part are encouraged to investigate whether the latest versions of these documents can be used. For any undated referenced document, the latest version applies to this part.
GB/T 2828.1-2003 Counted sample inspection procedure Part 1: Sample plan for batch inspection based on the AQL (ISO 2859-1.1999, IDT)
GB/T 2828.3-2008 Counted sample inspection procedure Part 3: Skip batch splitting procedure (ISO 2 859-3:2005, II)T) GB/T2828.4-2008 Attribute sampling inspection procedures Part 4: Procedure for assessment of claimed quality level (ISO2859-4-2002.M0D)
GB/T16306-2008 Procedure for assessment of claimed quality level re-inspection and re-verification 1S035341:2006 Statistical vocabulary and symbols Part 1: General statistical terms and terms used in probability ISO3534-2; 2006 Statistical vocabulary and symbols Part 2: Applied statistics 3 Terms, definitions, symbols and abbreviations
GB/T 2828.11—2003, ISO 3534-1:2006 and ISO 35342:2006, as well as the following terms, definitions and symbols, apply to the following parts of GB/T 2828.11—2008
3.1 Terms and definitions
Declared quality level The upper limit of the number of nonconforming products allowed in the total. 3.1.2
Nonconformity
Nonconformity Failure to meet specified requirements.
According to the importance of the post-quality characteristics of the unit product or the severity of the nonconformity of the quality characteristics, nonconformities can be divided into: Class A nonconformity, Class B nonconformity and Class C nonconformity.
Limiting numher of nonconforming itemsThe maximum number of nonconforming items allowed in the sample of the audit population under study, based on the claimed quality level. 3. 1, 4
Audit population
The total number of unit products audited. 3. 1. 5
Audit population confornity
The actual number of nonconforming items in the audit population is less than or equal to the claimed quality level, 3. 1.6
Audit population nonconformityThe actual number of nonconforming items in the audit population is less than or equal to the claimed quality level, 3. 1.7
re-test
Retest of the original sample.
re-inspection
Re-testing is to take samples from the original inspection population for inspection again to determine whether the inspection population is qualified. 3.1.9
quality level qualitylevel
The actual number of unqualified products in the inspection population. 3.1.10
audit sampling is the probability of the inspection population being judged as unqualified when the quality level of the inspection population is lower than the claimed quality level DQL. 3.2 Symbols and abbreviations
The symbols and abbreviations used in this part are as follows: DQL claimed quality level
1 limit of number of nonconforming items
n sample size
(n;L) sampling plan
N total size of verification
) number of nonconforming items in the verification population
number of nonconforming items in the sample
P. (D) actual quality level of the verification population
the probability of judging the verification population as passed according to the sampling plan when the verification is equal to D, 2
α probability of type 2 error (risk of misjudgment)
B probability of type 1 error (risk of missed judgment)
4 principle
GB/T 2828.11—2008
For any assessment based on sampling, due to the randomness of the samples, the judgment results will have inherent uncertainty. The procedures provided in this part of GB/T2828 will only determine that the verification is unqualified when there is sufficient evidence that the actual quality level is inferior to the claimed quality level. These procedures are designed in such a way that when the actual quality level of the verification population is equal to or better than the claimed quality level, the risk of judging the verification population to be unqualified is controlled at approximately 5%. When the actual quality level is inferior to the claimed quality level, the risk of judging the verification to be passed depends on the actual quality level. Claimed quality level
For products produced in batches, the overall quality requirements for the products should be specified in the product standards. When the supplier accepts the inspection, under the premise that the supplier is sure, the supplier's marketed quality level DQL value should not be greater than the product's overall quality level value required in the product standard. When the responsible department proposes the inspection, the specified higher quality level QI. value should not be less than the product's overall quality level value required in the product standard. When a certain type of non-conformity is specified as TQL, it means that the supplier has sufficient reason to believe that its product quality level is not worse than the DQI.
6 Procedures for implementing inspection sampling inspection
6.1 Determine the inspection population
Determine the inspection population according to the inspection needs. The products in the inspection population can be products of the same manufacturer, the same model, and the same cycle, or products of the same manufacturer, the same model, and different cycles, or products of the same manufacturer, different models, and different cycles, or similar products of different manufacturers, different models, and different cycles. If necessary, it can also be different types of products. 6.2 Determine the technical performance, quality characteristics and requirements of the unit product. According to the relevant standards, the technical performance and indicators, safety and health indicators of the unit product and other quality characteristics that need to be verified shall be clearly specified. 6.3 Determine the classification of non-conforming products
6.3.1 The classification of non-conforming products during the verification sample inspection shall be consistent with the classification of non-conforming products during the acceptance sample inspection. 6.3.2 According to the actual situation, non-conforming products are generally divided into three categories: Class A, Class B and Class C. If necessary, it can be divided into more than one or three categories of non-conforming products. In the case of a relatively simple unit production station, it can also be divided into two categories of non-conforming products, or even no category is distinguished.
6.4 Specify the claimed quality level
The inspected party shall declare the claimed quality level or the responsible department shall specify the claimed quality level according to the needs of the inspection. 6.4.1 When the inspected party reports DQT. by itself, the reported QI shall have sufficient basis and shall not be changed at will. 6.4.2 When the responsible department determines the claimed quality level according to the verification needs, the author has determined the AQL value when accepting the sample, then the determined QL value shall not be less than the corresponding AQ value.
6.5 Specified inspection level
GJ3/T2828 This part gives two inspection levels. The higher the inspection level, the larger the sample size required and the higher the inspection efficiency. The responsible department shall select the inspection level based on the two factors of the sample size that the ship can bear and the inspection efficiency. Once the inspection level is selected, it shall not be changed during the implementation process.
6.6 Retrieve sampling plan
According to the IDQL value and the inspection level, retrieve the sampling plan from Table 3.: For a given set of IJQI. values and inspection levels, if the sampling plan is subtracted, follow the arrow to retrieve the sampling plan. With the approval of the responsible department, for a certain DQI value,A sampling plan with a larger sample size may be used to replace a sampling plan with a smaller sample size. 3
GB/T 2828. 11—2008
6.7 Sampling
The samples shall be randomly selected from the verification population according to the method specified in GB3/T 10111. When stratified random sampling is used, the number of sample products taken from each layer shall be proportional to the size of the layer of the verification population under consideration. When sampling from the verification population (batch), stratified sampling can be used with identifiable batches as layers. When sampling from the process, stratified sampling can be used according to the identified sources of variation (for example, tools, operators, shifts, etc.). If the sample size of the retrieved sampling plan exceeds the size of the verification population under study, the unit products in the verification population shall be inspected.
6.8 Inspection samples
For each inspection item specified in advance, the relevant standards and technical requirements shall be followed. The inspection method is to inspect each sample in the sample one by one, and count the number of unqualified products in the inspected samples, or count the number of unqualified products of different categories in the samples separately. The test results should be recorded neatly and accurately.
6.9 Disposal of unqualified products
Any unqualified products found in the work sample should not be put back into the inspection. 6.10 Judgment criteria
The number of unit products inspected should be equal to the sample size specified in the sample plan table. If the number of unqualified products d found in the sample is less than or equal to the limit number of unqualified products L, the sample meets the requirements and the inspection is passed. If the number of unqualified products found in the work sample is greater than the limit number of unqualified products L, the sample meets the requirements and the inspection is passed. The inspection population is judged to be unqualified: If the inspected party has any objection to the judgment result, it may apply for re-inspection or re-testing. 6.11 Statistical interpretation of random inspection conclusions
When the sample size of the sampling plan is small, there is a high probability that the unqualified inspection population will be judged as passed, so its inspection conclusion should be "the market quality level of the inspection population is not negative", and should not be "the inspection population is qualified". The responsible party shall not be responsible for the overall qualified inspection population that is judged to have passed.
6.12 Re-inspection and re-testing
If the inspected party has any objection to the inspection conclusion, it may apply for re-inspection or re-testing. The re-inspection results obtained in accordance with GB/T163-6 are used as the final results of the sample quality and characteristics: re-inspection The inspection sample does not include the sample products of the initial inspection sample: - point re-inspection sampling plan (B/T16306's specified procedure retrieves the re-inspection sampling plan. The re-inspection conclusion is the final conclusion. Note: After re-inspection, the probability of the first type of error in sampling inspection will be reduced, and the probability of the second type of error in sampling inspection will be increased. 6.13 Judgment by actual quality level
When the actual quality level of the inspection population can be determined, the actual quality level of the inspection population should be compared with the claimed quality level DQL to determine whether the inspection population is unqualified, without using the sampling plan to judge; at this time there is no re-inspection, and re-inspection is allowed. 7 Sampling characteristic function and test power of sampling plan Table D of this part: ~ Table D, 24 gives the sampling characteristic function of the sampling plan (based on the suspected geometric distribution): when D~D(>DQL), they can find out the value of the probability of passing the inspection P, (D, of the corresponding sampling plan, where 1-P, (DI) is the test power of the sampling plan when D-D.
8 Application Examples
Example 1: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 2, that is, DQI: 2. Try to determine the sampling plan.
If the sampling plan with inspection level () is selected, the sampling plan obtained from Table B.1 is (n, L)(2.0). That is, 2 samples of products are randomly selected from the inspection population for inspection. If there are no unqualified products, the inspection is judged to be passed; if there are unqualified products, the inspection population is judged to be unqualified.
GB/T2828.112008
Example 2: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 5, that is, DL=5. Try to determine its interpretation plan.
If the sampling plan with inspection level O is selected, there is an upward arrow at the intersection of the column of N=80 and the row of DQI…5 in Table B. Following the direction of the arrow, we can find that the required sampling plan is (n,L)=(1.0). Randomly select 1 sample product from the inspection population for inspection. If it is a qualified product, the inspection is judged to have passed; if it is a defective product, the inspection population is judged to have failed. If the sampling plan with inspection level -1 is selected, refer to Table B.2. At the intersection of the column of N=80 and the row of DQI.5, the sampling plan is (n,L)=（5.,1）. Randomly select 6 sample products from the inspection population for inspection. If the number of defective products does not exceed 1, the inspection is judged to have passed; if the number of defective products is greater than -1, the inspection population is judged to have failed. The efficacy of the above two sampling plans is different. From Table D.12, when the inspection population contains 31 defective products, the efficacy of the sampling plan (n,L)(1,0) is 1-P,(30)1-0.625 C=C.375 0; The power of sampling scheme (n, L) = (6, 1) is 1-P (30) = 1-0.2644 = 9,7356. The power of sampling scheme (5.1) is significantly higher than that of sampling scheme (1, 0). The responsible department should comprehensively consider the power, economy and other factors to determine the best sampling scheme. Example 3: If a certain product population has 178 units, and it is to be tested whether the number of non-conforming products is more than 2, that is, 11-=2, the sampling plan is determined. If the sampling plan with inspection level 0 is selected, check Table B.=. Because 178 is between 170 and 190, the sampling plan corresponding to N = 190 should be used (n.1)-(5,)
Example 1: A certain product population has 45 units, and the claimed quality level DQI: 5. The sampling plan is determined: the sampling plan with inspection level 1 is selected. From Table B.2, the sampling plan is (n, L)--(4, 1). When the inspection population actually contains 20 non-conforming products, check Table D.8 to get P, (20)=0.3935. Therefore, when D=20, the power of the sampling plan is 1-0.3936-0.6064. 5
GB/T 2828.11—-2008
Appendix A
(Normative Appendix)
Case where the claimed quality level IQL is equal to 0 If the unit products in the audit population have passed the supplier's U0% inspection or the audited party believes that all the unit products in the audit population are qualified, the claimed quality level DQI0 can be specified when conducting quality inspection on this population. When the claimed quality level -DQIC is specified, the sampling scheme (n,L)=(n,0) is used, and the value of n can be selected from 1-~N according to actual needs. When d>, the audit population is judged to be unqualified. II re-inspection is not allowed. When α=0, it can only be judged to be passed. Its inspection conclusion should be " It does not negate its claim of quality.
When DQL=0 is specified, random sampling may not be used, but sampling may be carried out based on professional knowledge or experience. 6
Appendix B
(Normative Appendix)
Sampling Plan 1
Table B.1 Sampling Plan for the Oth Inspection Level L=0
GB/T 2828.11—2008
1150120
90-2101230
CB/T 2828.11-2068
Table B.2 Sampling Plan for the Ith Inspection Level L=1
J40130-170
902102302.410 Judgment criteria
The number of unit products inspected should be equal to the sample size specified in the sampling plan. If the number of unqualified products d found in the sample is less than or equal to the limit number of unqualified products L, the sample meets the requirements and is judged to have passed the inspection. If the number of unqualified products found in the sample is greater than the limit number of unqualified products L, the sample does not meet the requirements and the inspection population is judged to be unqualified: If the inspected party has objections to the judgment result, it can request re-inspection or re-testing. 6.11 Statistical interpretation of sampling conclusion
When the sample size of the sampling plan is small, there is a high probability that the unqualified inspection population will be judged as passed, so its inspection conclusion should be "not denying the market quality level of the inspection population", not "the inspection population is qualified". The responsible party shall not be responsible for judging the inspection population that has passed the inspection as qualified.
6.12 Retest and re-inspection
If the party under inspection has any disagreement with the inspection conclusion, it may apply for retest or re-inspection. The retest results obtained in accordance with the provisions of GB/T16366 shall be used as the final results of the sample quality and characteristics: the retest samples are not the same as the sample products of the initial inspection samples: - point retest sampling plan (B/T16306) according to the specified procedure to retrieve the retest sampling plan. The retest conclusion is the final conclusion. Note: After re-inspection, the probability of the first type of error in sampling inspection will be reduced, and the probability of the second type of error in sampling inspection will be increased. 6.13 Judgment by actual quality level
When the actual quality level of the inspection population can be determined, the actual quality level of the inspection population shall be compared with the claimed quality level DQL to determine whether the inspection population is unqualified, without using the sampling plan to judge; at this time, there is no retest, and re-inspection is allowed. 7 Sampling characteristics of the sampling plan and test efficiency Table D of this part: ~ Table D, 24 Given the sampling characteristic deviations of the sampling scheme (based on the suspected geometric distribution): when D~D(>DQL), they can be used to find the value of the probability of passing the corresponding sampling scheme, P,(D,), where 1-P,(DI) is the value when D-D The inspection efficiency of the sampling scheme.
8 Application examples
Example 1: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 2, that is, DQI: 2. Try to determine the sampling scheme.
If the sampling scheme with inspection level () is selected, the sampling scheme obtained from Table B.1 is (n, L)(2.0). That is, 2 samples of products are randomly selected from the inspection population for inspection. If there are no unqualified products, the inspection is judged to be passed; if there are unqualified products, the inspection population is judged to be unqualified.
GB/T2828.112008
Example 2: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 5, that is, DL=5. Try to determine its interpretation scheme.
If the sampling scheme with inspection level O is selected, it is obtained from Table B.1 that N=80 The intersection of the column of N=80 and the row of DQI.5 is an upward arrow. Following the direction of the arrow, we can find that the required sampling plan is (n,L)=(1.0). Randomly select a sample product from the inspection population for inspection. If it is a qualified product, the inspection is judged to have passed; if it is a failed product, the inspection population is judged to have failed. If the sampling plan with inspection level -1 is selected, we can refer to Table B.2. At the intersection of the column of N=80 and the row of DQI.5, we can find that the required sampling plan is (n,L)= (5.,1), randomly pick 6 sample products from the inspection population for inspection. If the number of unqualified products does not exceed 1, the inspection is considered passed; if the number of unqualified products is greater than -1, the inspection population is considered unqualified. The efficacy of the above two sampling plans is different. From Table D.12, when the inspection population contains 31 unqualified products, the efficacy of the sampling plan (n,L) (1,0) is 1-P, (30) 1-0.625 C = C.375 0; the efficacy of the sampling plan (n,L) = (6,1) is 1-P (30) = 1-0.2644 = 9,7356. The efficacy of the sampling plan (5.1) is significantly higher than that of the sampling plan (1,0). The responsible department should comprehensively consider the efficacy, economy and other factors to determine the best sampling plan. Example 3: If a certain product population has 178 units, and it is to be tested whether the number of non-conforming products is more than 2, that is, 11-=2, the sampling plan is determined. If the sampling plan with inspection level 0 is selected, check Table B.=. Because 178 is between 170 and 190, the sampling plan corresponding to N = 190 should be used (n.1)-(5,)
Example 1: A certain product population has 45 units, and the claimed quality level DQI: 5. The sampling plan is determined: the sampling plan with inspection level 1 is selected. From Table B.2, the sampling plan is (n, L)--(4, 1). When the inspection population actually contains 20 non-conforming products, check Table D.8 to get P, (20)=0.3935. Therefore, when D=20, the power of the sampling plan is 1-0.3936-0.6064. 5
GB/T 2828.11—-2008
Appendix A
(Normative Appendix)
Case where the claimed quality level IQL is equal to 0 If the unit products in the audit population have passed the supplier's U0% inspection or the audited party believes that all the unit products in the audit population are qualified, the claimed quality level DQI0 can be specified when conducting quality inspection on this population. When the claimed quality level -DQIC is specified, the sampling scheme (n,L)=(n,0) is used, and the value of n can be selected from 1-~N according to actual needs. When d>, the audit population is judged to be unqualified. II re-inspection is not allowed. When α=0, it can only be judged to be passed. Its inspection conclusion should be " It does not negate its claim of quality.
When DQL=0 is specified, random sampling may not be used, but sampling may be carried out based on professional knowledge or experience. 6
Appendix B
(Normative Appendix)
Sampling Plan 1
Table B.1 Sampling Plan for the Oth Inspection Level L=0
GB/T 2828.11—2008
1150120
90-2101230
CB/T 2828.11-2068
Table B.2 Sampling Plan for the Ith Inspection Level L=1
J40130-170
902102302.410 Judgment criteria
The number of unit products inspected should be equal to the sample size specified in the sampling plan. If the number of unqualified products d found in the sample is less than or equal to the limit number of unqualified products L, the sample meets the requirements and is judged to have passed the inspection. If the number of unqualified products found in the sample is greater than the limit number of unqualified products L, the sample does not meet the requirements and the inspection population is judged to be unqualified: If the inspected party has objections to the judgment result, it can request re-inspection or re-testing. 6.11 Statistical interpretation of sampling conclusion
When the sample size of the sampling plan is small, there is a high probability that the unqualified inspection population will be judged as passed, so its inspection conclusion should be "not denying the market quality level of the inspection population", not "the inspection population is qualified". The responsible party shall not be responsible for judging the inspection population that has passed the inspection as qualified.
6.12 Retest and re-inspection
If the party under inspection has any disagreement with the inspection conclusion, it may apply for retest or re-inspection. The retest results obtained in accordance with the provisions of GB/T16366 shall be used as the final results of the sample quality and characteristics: the retest samples are not the same as the sample products of the initial inspection samples: - point retest sampling plan (B/T16306) according to the specified procedure to retrieve the retest sampling plan. The retest conclusion is the final conclusion. Note: After re-inspection, the probability of the first type of error in sampling inspection will be reduced, and the probability of the second type of error in sampling inspection will be increased. 6.13 Judgment by actual quality level
When the actual quality level of the inspection population can be determined, the actual quality level of the inspection population shall be compared with the claimed quality level DQL to determine whether the inspection population is unqualified, without using the sampling plan to judge; at this time, there is no retest, and re-inspection is allowed. 7 Sampling characteristics of the sampling plan and test efficiency Table D of this part: ~ Table D, 24 Given the sampling characteristic deviations of the sampling scheme (based on the suspected geometric distribution): when D~D(>DQL), they can be used to find the value of the probability of passing the corresponding sampling scheme, P,(D,), where 1-P,(DI) is the value when D-D The inspection efficiency of the sampling scheme.
8 Application examples
Example 1: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 2, that is, DQI: 2. Try to determine the sampling scheme.
If the sampling scheme with inspection level () is selected, the sampling scheme obtained from Table B.1 is (n, L)(2.0). That is, 2 samples of products are randomly selected from the inspection population for inspection. If there are no unqualified products, the inspection is judged to be passed; if there are unqualified products, the inspection population is judged to be unqualified.
GB/T2828.112008
Example 2: There are 80 units of products in a certain inspection population. It is necessary to check whether the number of unqualified products exceeds 5, that is, DL=5. Try to determine its interpretation scheme.
If the sampling scheme with inspection level O is selected, it is obtained from Table B.1 that N=80 The intersection of the column of N=80 and the row of DQI.5 is an upward arrow. Following the direction of the arrow, we can find that the required sampling plan is (n,L)=(1.0). Randomly select a sample product from the inspection population for inspection. If it is a qualified product, the inspection is judged to have passed; if it is a failed product, the inspection population is judged to have failed. If the sampling plan with inspection level -1 is selected, we can refer to Table B.2. At the intersection of the column of N=80 and the row of DQI.5, we can find that the required sampling plan is (n,L)= (5.,1), randomly pick 6 sample products from the inspection population for inspection. If the number of unqualified products does not exceed 1, the inspection is considered passed; if the number of unqualified products is greater than -1, the inspection population is considered unqualified. The efficacy of the above two sampling plans is different. From Table D.12, when the inspection population contains 31 unqualified products, the efficacy of the sampling plan (n,L) (1,0) is 1-P, (30) 1-0.625 C = C.375 0; the efficacy of the sampling plan (n,L) = (6,1) is 1-P (30) = 1-0.2644 = 9,7356. The efficacy of the sampling plan (5.1) is significantly higher than that of the sampling plan (1,0). The responsible department should comprehensively consider the efficacy, economy and other factors to determine the best sampling plan. Example 3: If a certain product population has 178 units, and it is to be tested whether the number of non-conforming products is more than 2, that is, 11-=2, the sampling plan is determined. If the sampling plan with inspection level 0 is selected, check Table B.=. Because 178 is between 170 and 190, the sampling plan corresponding to N = 190 should be used (n.1)-(5,)
Example 1: A certain product population has 45 units, and the claimed quality level DQI: 5. The sampling plan is determined: the sampling plan with inspection level 1 is selected. From Table B.2, the sampling plan is (n, L)--(4, 1). When the inspection population actually contains 20 non-conforming products, check Table D.8 to get P, (20)=0.3935. Therefore, when D=20, the power of the sampling plan is 1-0.3936-0.6064. 5bzxZ.net
GB/T 2828.11—-2008
Appendix A
(Normative Appendix)
Case where the claimed quality level IQL is equal to 0 If the unit products in the audit population have passed the supplier's U0% inspection or the audited party believes that all the unit products in the audit population are qualified, the claimed quality level DQI0 can be specified when conducting quality inspection on this population. When the claimed quality level -DQIC is specified, the sampling scheme (n,L)=(n,0) is used, and the value of n can be selected from 1-~N according to actual needs. When d>, the audit population is judged to be unqualified. II re-inspection is not allowed. When α=0, it can only be judged to be passed. Its inspection conclusion should be " It does not negate its claim of quality.
When DQL=0 is specified, random sampling may not be used, but sampling may be carried out based on professional knowledge or experience. 6
Appendix B
(Normative Appendix)
Sampling Plan 1
Table B.1 Sampling Plan for the Oth Inspection Level L=0
GB/T 2828.11—2008
1150120
90-2101230
CB/T 2828.11-2068
Table B.2 Sampling Plan for the Ith Inspection Level L=1
J40130-170
902102302.4If there are no unqualified products, the inspection is judged to be passed; if there are unqualified products, the inspection population is judged to be unqualified.
GB/T2828.112008
Example 2: There are 80 units of products in the inspection population. It is necessary to check whether the number of unqualified products in the inspection is more than 5, that is, DL=5. Try to determine the sampling plan.
If the sampling plan with inspection level O is selected, the intersection of the column of N=80 and the row of DQI…5 in Table B is an upward arrow. Following the direction of the arrow, the required sampling plan is (n,L)=(1.0). Randomly select 1 sample product from the inspection population for inspection. If it is a qualified product, the inspection is judged to have passed; if it is a defective product, the inspection population is judged to have failed. If the sampling plan with inspection level -1 is selected, refer to Table B.2. At the intersection of the column of N=80 and the row of DQI.5, the sampling plan is (n,L)=（5.,1）. Randomly select 6 sample products from the inspection population for inspection. If the number of defective products does not exceed 1, the inspection is judged to have passed; if the number of defective products is greater than -1, the inspection population is judged to have failed. The efficacy of the above two sampling plans is different. From Table D.12, when the inspection population contains 31 defective products, the efficacy of the sampling plan (n,L)(1,0) is 1-P,(30)1-0.625 C=C.375 0; The power of sampling scheme (n, L) = (6, 1) is 1-P (30) = 1-0.2644 = 9,7356. The power of sampling scheme (5.1) is significantly higher than that of sampling scheme (1, 0). The responsible department should comprehensively consider the power, economy and other factors to determine the best sampling scheme. Example 3: If a certain product population has 178 units, and it is to be tested whether the number of non-conforming products is more than 2, that is, 11-=2, the sampling plan is determined. If the sampling plan with inspection level 0 is selected, check Table B.=. Because 178 is between 170 and 190, the sampling plan corresponding to N = 190 should be used (n.1)-(5,)
Example 1: A certain product population has 45 units, and the claimed quality level DQI: 5. The sampling plan is determined: the sampling plan with inspection level 1 is selected. From Table B.2, the sampling plan is (n, L)--(4, 1). When the inspection population actually contains 20 non-conforming products, check Table D.8 to get P, (20)=0.3935. Therefore, when D=20, the power of the sampling plan is 1-0.3936-0.6064. 5
GB/T 2828.11—-2008
Appendix A
(Normative Appendix)
Case where the claimed quality level IQL is equal to 0 If the unit products in the audit population have passed the supplier's U0% inspection or the audited party believes that all the unit products in the audit population are qualified, the claimed quality level DQI0 can be specified when conducting quality inspection on this population. When the claimed quality level -DQIC is specified, the sampling scheme (n,L)=(n,0) is used, and the value of n can be selected from 1-~N according to actual needs. When d>, the audit population is judged to be unqualified. II re-inspection is not allowed. When α=0, it can only be judged to be passed. Its inspection conclusion should be " It does not negate its claim of quality.
When DQL=0 is specified, random sampling may not be used, but sampling may be carried out based on professional knowledge or experience. 6
Appendix B
(Normative Appendix)
Sampling Plan 1
Table B.1 Sampling Plan for the Oth Inspection Level L=0
GB/T 2828.11—2008
1150120
90-2101230
CB/T 2828.11-2068
Table B.2 Sampling Plan for the Ith Inspection Level L=1
J40130-170
902102302.4If there are no unqualified products, the inspection is judged to be passed; if there are unqualified products, the inspection population is judged to be unqualified.
GB/T2828.112008
Example 2: There are 80 units of products in the inspection population. It is necessary to check whether the number of unqualified products in the inspection is more than 5, that is, DL=5. Try to determine the sampling plan.
If the sampling plan with inspection level O is selected, the intersection of the column of N=80 and the row of DQI…5 in Table B is an upward arrow. Following the direction of the arrow, the required sampling plan is (n,L)=(1.0). Randomly select 1 sample product from the inspection population for inspection. If it is a qualified product, the inspection is judged to have passed; if it is a defective product, the inspection population is judged to have failed. If the sampling plan with inspection level -1 is selected, refer to Table B.2. At the intersection of the column of N=80 and the row of DQI.5, the sampling plan is (n,L)=（5.,1）. Randomly select 6 sample products from the inspection population for inspection. If the number of defective products does not exceed 1, the inspection is judged to have passed; if the number of defective products is greater than -1, the inspection population is judged to have failed. The efficacy of the above two sampling plans is different. From Table D.12, when the inspection population contains 31 defective products, the efficacy of the sampling plan (n,L)(1,0) is 1-P,(30)1-0.625 C=C.375 0; The power of sampling scheme (n, L) = (6, 1) is 1-P (30) = 1-0.2644 = 9,7356. The power of sampling scheme (5.1) is significantly higher than that of sampling scheme (1, 0). The responsible department should comprehensively consider the power, economy and other factors to determine the best sampling scheme. Example 3: If a certain product population has 178 units, and it is to be tested whether the number of non-conforming products is more than 2, that is, 11-=2, the sampling plan is determined. If the sampling plan with inspection level 0 is selected, check Table B.=. Because 178 is between 170 and 190, the sampling plan corresponding to N = 190 should be used (n.1)-(5,)
Example 1: A certain product population has 45 units, and the claimed quality level DQI: 5. The sampling plan is determined: the sampling plan with inspection level 1 is selected. From Table B.2, the sampling plan is (n, L)--(4, 1). When the inspection population actually contains 20 non-conforming products, check Table D.8 to get P, (20)=0.3935. Therefore, when D=20, the power of the sampling plan is 1-0.3936-0.6064. 5
GB/T 2828.11—-2008
Appendix A
(Normative Appendix)
Case where the claimed quality level IQL is equal to 0 If the unit products in the audit population have passed the supplier's U0% inspection or the audited party believes that all the unit products in the audit population are qualified, the claimed quality level DQI0 can be specified when conducting quality inspection on this population. When the claimed quality level -DQIC is specified, the sampling scheme (n,L)=(n,0) is used, and the value of n can be selected from 1-~N according to actual needs. When d>, the audit population is judged to be unqualified. II re-inspection is not allowed. When α=0, it can only be judged to be passed. Its inspection conclusion should be " It does not negate its claim of quality.
When DQL=0 is specified, random sampling may not be used, but sampling may be carried out based on professional knowledge or experience. 6
Appendix B
(Normative Appendix)
Sampling Plan 1
Table B.1 Sampling Plan for the Oth Inspection Level L=0
GB/T 2828.11—2008
1150120
90-2101230
CB/T 2828.11-2068
Table B.2 Sampling Plan for the Ith Inspection Level L=1
J40130-170
902102302.4
Tip: This standard content only shows part of the intercepted content of the complete standard. If you need the complete standard, please go to the top to download the complete standard document for free.