Multiattribute acceptance sampling plans - Library(ISI Kolkata ...
Multiattribute acceptance sampling plans - Library(ISI Kolkata ...
Multiattribute acceptance sampling plans - Library(ISI Kolkata ...
Create successful ePaper yourself
Turn your PDF publications into a flip-book with our unique Google optimized e-Paper software.
a shirt with a button missing or a shirt with a wrong button), or when defects are classified<br />
in mutually exclusive classes e.g. critical, major or minor. It would therefore be necessary<br />
to take care of both the situations.<br />
As stated earlier that the primary focus of the present enquiry is to examine different alternative<br />
<strong>acceptance</strong> criteria rather than to locate an optimal plan in a given set up and<br />
to develop search alogorithm for the mentioned purpose. We make use of the cost models<br />
developed by Majumdar(1980), Majumdar(1990) and Majumdar (1997). The cost models<br />
mentioned along with some elementary results in the following chapter of the part have already<br />
been published as noted here.<br />
2.1.4 A generalized cost model for nondestructive testing<br />
In our case we take a sample of size n and inspect each item for all the attributes. We<br />
observe x i ; i = 1, 2, .., r. as the number of defectives on the i th attribute. We denote the<br />
vector (x 1 , x 2 , ..., x r ) as x. We define set A as the set of x for which we declare the lot as<br />
acceptable. Let Ā be the complementary set for which we reject the lot. Let X i; denotes the<br />
number of defectives on i th characteristic in the lot, i = 1, 2, ..., r.<br />
Let the costs be<br />
when x ∈ A<br />
r∑<br />
r∑<br />
C(x) = nS 0 + x i S i + (N − n)A 0 + (X i − x i )A i<br />
i=1<br />
i=1<br />
... (2.1.1)<br />
r∑<br />
r∑<br />
C(x) = nS 0 + x i S i + (N − n)R 0 + (X i − x i )R i<br />
i=1<br />
i=1<br />
when x ∈ Ā ...(2.1.2)<br />
The interpretations of cost parameters are as follows: S 0 is the common cost of inspection<br />
i.e. <strong>sampling</strong> and testing cost per item in the sample for all the characterstics put together;<br />
x i S i the cost proportional to the number of defectives of i th type in the sample which is<br />
the additional cost for an inspected item containing defects of i th type.<br />
The cost of <strong>acceptance</strong> is composed of two parts; (N − n)A 0 is cost proprtional to the<br />
r∑<br />
items in the remainder of the lot, and another part (X i − x i )A i where A i is the cost<br />
of accepting an item containing defective for i th attribute.<br />
i=1<br />
We assume the loss due to<br />
81