Chapter 2 Modelling Quality and Warranty Cost - Mathematics in ...
Chapter 2 Modelling Quality and Warranty Cost - Mathematics in ...
Chapter 2 Modelling Quality and Warranty Cost - Mathematics in ...
You also want an ePaper? Increase the reach of your titles
YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.
xHUÀ¼¦½ SLF7JOvL JOw#LMJ xHH‚º¦¿<br />
³j»F£JOvLMJTw#LMJ<br />
JMxHVUÀ¼¿<br />
³j»F7JTwLMJOw#L<br />
Û<br />
H|ÜÞÝß à FÝE F DMHn/J FDIHH.L<br />
opt<br />
36 CHAPTER 2. MODELLING QUALITY AND WARRANTY COST<br />
25<br />
Hardware <strong>Warranty</strong> <strong>Cost</strong>s v/s q2, q3=0.8<br />
10<br />
Hardware Wararnty <strong>Cost</strong>s v/s q2, q1=0.3<br />
30<br />
Hardware <strong>Warranty</strong> <strong>Cost</strong>s v/s q1, q2=0.3<br />
20<br />
9.5<br />
25<br />
9<br />
20<br />
15<br />
8.5<br />
15<br />
10<br />
8<br />
5<br />
q1=0.1<br />
q1=0.5<br />
q1=0.8<br />
7.5<br />
7<br />
q3=0.1<br />
q3=0.5<br />
q3=0.8<br />
10<br />
5<br />
q3=0.1<br />
q3=0.5<br />
q3=0.8<br />
0<br />
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1<br />
Infant Mortality Factor q2<br />
6.5<br />
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1<br />
Infant Mortality Factor q2<br />
0<br />
0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1<br />
Component Failure Rate q1<br />
(a) (b) (c)<br />
Figure 2.6: (a) Trends J <strong>in</strong> hw with component JMK quality <strong>and</strong> JON IMF (JOP , fixed). (b) Trends J <strong>in</strong> hw<br />
with JTN IMF <strong>and</strong> diagnostics JOP capability (JMK , fixed). (c) Trends J <strong>in</strong> hw with component JMK quality <strong>and</strong><br />
diagnostics JOP capability (JON , fixed).<br />
2.5.2 The Software <strong>Warranty</strong> <strong>Cost</strong>s<br />
The software warranty costs are characterized <strong>in</strong> terms of the severity levels of the software failures,<br />
SL (see Section 2.3.2). Therefore, given the operat<strong>in</strong>g range of the quality vector D , we can calculate<br />
from our SL model the probabilities Êv , Ê)w , ÊŽx , Êy of failures of SL HZ_ (catastrophic) through SL H®{<br />
(m<strong>in</strong>or) respectively (see Table 2.1). Associated with each of these types of failures is a warranty cost,<br />
Ëv , Ëw , ˆx <strong>and</strong> Ëy respectively. The warranty cost for software is expressed by:<br />
J sw FDMHVH J FO_e…JOvH_F¯Êv>ËvVnÔÊw.ËwVnÕÊŽx7ˆxÐnÕÊ)y>Ëy_H.Q (2.10)<br />
The SDE most significantly impacts the warranty cost of the software. A higher SDE means fewer<br />
catastrophic failures. The probabilities Êic , º„H|lLMQMQMQL ² are fixed for a given operational range of JOv , JOw ,<br />
, <strong>and</strong> are chosen accord<strong>in</strong>g to our model of the Severity Level function (2.7). Recall that JTy <strong>and</strong> JOS<br />
JMx<br />
are given by expression (2.6). More precisely,<br />
n…סc<br />
ÊicŒÖ~gdH<br />
¼ÅYRH F£]Q¯²L_5HÙØ F']Q{)L ]Q¯ÚHÍØ F']Q¯ÚL_+H where . The וc quantities are <strong>in</strong>troduced to account for other<br />
lower-order effects, which are not accounted for dur<strong>in</strong>g the production. These <strong>in</strong>clude effects such as<br />
a product be<strong>in</strong>g returned due to <strong>in</strong>correct usage by the customer. One may also use a model allow<strong>in</strong>g<br />
more flexibility, such as (2.9). Unfortunately, <strong>in</strong> such a model the probabilities will need to be<br />
computed as functions JOc of .<br />
2.6 The Complete Model<br />
We now summarize the models of the previous sections. Recall that the goal was to identify the various<br />
functions <strong>in</strong> the optimization problem (2.1) repeated here for convenience