Abstract
In this paper, we present two new dependent mixed sampling plans based on the process yield index for linear profiles. A mixed sampling plan includes two stages, the first stage is tested by variables and attributes combined and the second stage is tested by attributes only. The first plan is based on the traditional mixed sampling scheme and the second plan is based on the modified mixed sampling scheme with marginal quality. If a lot is very bad, the probability it can be rejected with small initial sample is higher for dependent mixed sampling with marginal quality. The plan parameters are determined by a nonlinear optimization model that the criterion considered is the specification of two points on the operating characteristic curve. A search algorithm is used to solve the nonlinear optimization model. We found that the number of profiles required in the first stage is much smaller than in the second stage. Two examples are used to illustrate the proposed method.
| Original language | English |
|---|---|
| Pages | 594-600 |
| Number of pages | 7 |
| State | Published - 2020 |
| Event | 2016 Industrial and Systems Engineering Research Conference, ISERC 2016 - Anaheim, United States Duration: 21 05 2016 → 24 05 2016 |
Conference
| Conference | 2016 Industrial and Systems Engineering Research Conference, ISERC 2016 |
|---|---|
| Country/Territory | United States |
| City | Anaheim |
| Period | 21/05/16 → 24/05/16 |
Bibliographical note
Publisher Copyright:© 2016 Proceedings of the 2016 Industrial and Systems Engineering Research Conference, ISERC 2016. All rights reserved.
Keywords
- Dependent mixed sampling plan
- Linear profiles
- Marginal quality
- Yield index