14_Attribute Plans

14_Attribute Plans - Spring 2008 Lecture Notes - EMSE 182,...

Info iconThis preview shows pages 1–7. Sign up to view the full content.

View Full Document Right Arrow Icon
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 1 ACCEPTANCE SAMPLING ATTRIBUTE CASE ASPECTS OF ACCEPTANCE SAMPLING Its purpose is to sentence lots not estimate their quality. It does not provide a direct form of quality control. It is not used to “inspect quality into a product" but to ensure output quality.
Background image of page 1

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 2 MAIN APPROACHES No inspection • Lot quality is usually of very good quality i.e. past experience with good vendor • No economic justification for inspection, i.e. lots used in making non-critical component or associated failure cost very low 100% inspection • Lot quality is highly variable or of poor quality • Lots used to make critical component • Product failure costs high Acceptance Sampling • Destructive testing • Cost of 100% inspection too high • Error rate of 100% inspection too high • Demonstrated low process capability by vendor • Put psychological/economic pressure on vendor • Note that with acceptance sampling - there is a risk of accepting bad lots and rejecting good lots - less information about lot quality is obtained than if 100% inspection is done ÐÑ - requires careful planning and documentation - requires random sampling from lots OVERVIEW OF SAMPLING
Background image of page 2
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 3 Attribute vs. Variable Single Stage vs. Multiple Stage vs Sequential SAMPLING FROM LOTS Lots Should be • Homogeneous (same inputs for the outputs - materials, machines, operators) • The larger the better (more economical, less variability) • Conformable to materials handling systems (the less handling the better) Sampling should be random, avoid temptation for easy access sampling. Use randomly assigned or selected numbers or stratified sampling.
Background image of page 3

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 4 SINGLE SAMPLING PLANS Method: From a batch of size N, select a random sample of size n and define an acceptance number c. Then for the number of unacceptable items D, if D c accept D c reject œ Ÿ D c accept sample n D c reject Ÿ Note that for attribute case a lot is rejected if it fails to satisfy any of possibly several go no-go criteria. Models Pr D d p 1 p if N is large wrt n if N is not large wrt n Öœ × œ ÐÑ Ú Ý Ý Û Ý Ý Ü Š‹ n d dn d Š pN 1 p N d N n most often the binomial model is used for its simplicity.
Background image of page 4
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 5 The OC Curve: is a plot of the probability of acceptance P verses the probability of a a nonconforming item p where Pr D c p 1 p Type B OC Curves Type A OC Curves ÖŸ × œ ÐÑ Ú Ý Ý Ý Û Ý Ý Ý Ü ± Š‹ ± d0 c n d dn d c œ œ Š pN 1 p N d N n
Background image of page 5

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
Spring 2008 Lecture Notes - EMSE 182, 282 - Professor Jim Harris - 6 • Notes about the OC curve - P is a function of p, p is unknown.
Background image of page 6
Image of page 7
This is the end of the preview. Sign up to access the rest of the document.

This note was uploaded on 01/02/2010 for the course EMSE 282 taught by Professor Harris during the Spring '07 term at GWU.

Page1 / 42

14_Attribute Plans - Spring 2008 Lecture Notes - EMSE 182,...

This preview shows document pages 1 - 7. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online