Download as pdf or txt
Download as pdf or txt
You are on page 1of 6

(a)

m m
n  150; m  20;  Di  50; p   Di mn  50 20(150)  0.0167
i 1 i 1

UCL  p  3 p (1  p ) n  0.0167  3 0.0167(1  0.0167) 150  0.0480


LCL  p  3 p (1  p ) n  0.0167  3 0.0167(1  0.0167) 150  0.0167  0.0314  0

MTB > Stat > Control Charts > Attributes Charts > P

The process appears to be in statistical control.

(b)
Using Equation 7.12,
(1  p ) 2
n L
p
(1  0.0167) 2
 (3)
0.0167
 529.9 Select n  530.
(a)
p  0.07; k  3 sigma control limits; n  400
UCL  p  3 p(1  p) n  0.07  3 0.07(1  0.07) 400  0.108
LCL  p  3 p(1  p ) n  0.07  3 0.07(1  0.07) 400  0.032

(b)
npnew = 400(0.10) = > 40, so use the normal approximation to the binomial.
Pr{detect on 1st sample}  1  Pr{not detect on 1st sample}
 1 
 1  [Pr{ pˆ  UCL | p}  Pr{ pˆ  LCL | p}]
 UCL  p   LCL  p 
 1     
 p (1  p ) n   p (1  p ) n 
   
 0.108  0.1   0.032  0.1 
 1     
 0.1(1  0.1) 400   0.1(1  0.1) 400 
   
 1   (0.533)   (4.533)
 1  0.703  0.000
 0.297

(c)
Pr{detect on 1st or 2nd sample}
= Pr{detect on 1st} + Pr{not on 1st}Pr{detect on 2nd}
= 0.297 + (1 – 0.297)(0.297)
= 0.506
(a)
Plot the number of nonconformities per water heater on a c chart.
CL  c   D m  924 /176  5.25
UCL  c  3 c  5.25  3 5.25  12.12
LCL  0
Plot the results after inspection of each water heater, approximately 8/day.

(b)
Let new inspection unit n = 2 water heaters
CL  nc  2(5.25)  10.5
UCL  nc  3 nc  10.5  3 10.5  20.22
LCL  nc  3 nc  10.5  3 10.5  0.78

(c)
Pr{type I error}  Pr{D  LCL | c}  Pr{D  UCL | c}
 Pr{D  0.78 |10.5}  1  Pr{D  20.22 |10.5}
 POI(0,10.5)  1  POI(20,10.5) 
 0.000  1  0.997 
 0.003
ˆ  x  100; s  1.05; ˆ x  s c4  1.05 0.9400  1.117

(a)
USL  LSL (95  10)  (95  10)
Potential: Cˆ p    2.98
6ˆ 6(1.117)

(b)
ˆ  LSL x 100  (95  10)
Cˆ pl    4.48
3ˆ x 3(1.117)
USL x  ˆ (95  10)  100
Actual: Cˆ pu    1.49
3ˆ x 3(1.117)
Cˆ  min(Cˆ , Cˆ )  1.49
pk pl pu

(c)
pˆ Actual  Pr{x  LSL}  Pr{x  USL}
 Pr{x  LSL}  1  Pr{x  USL}
 LSL  ˆ    USL  ˆ 
 Pr  z    1  Pr  z  
 ˆ    ˆ 
 85  100    105  100 
 Pr  z    1  Pr  z  
 1.117    1.117 
  (13.429)  1   (4.476) 
 0.0000  1  0.999996
 0.000004
 85  95    105  95 
pˆ Potential  Pr  z    1  Pr  z  
 1.117    1.117 
  (8.953)  1   (8.953) 
 0.000000  1  1.000000
 0.000000
(a)
N = 5000, n = 50, c = 2

p Pa=Pr{d<=1} Pr{reject}
0.0010 0.99998 0.00002
0.0020 0.99985 0.00015
0.0030 0.99952 0.00048
0.0040 0.99891 0.00109
0.0050 0.99794 0.00206
0.0060 0.99657 0.00343
0.0070 0.99474 0.00526
0.0080 0.99242 0.00758
0.0090 0.98957 0.01043
0.0100 0.98618 0.01382
0.0200 0.92157 0.07843
0.0300 0.81080 0.18920
0.0400 0.67671 0.32329
0.0500 0.54053 0.45947
0.0600 0.41625 0.58375
0.0700 0.31079 0.68921
0.0800 0.22597 0.77403
0.0900 0.16054 0.83946
0.1000 0.11173 0.88827
0.1010 0.10764 0.89236
0.1020 0.10368 0.89632
0.1030 0.09985 0.90015
0.1040 0.09614 0.90386
0.1050 0.09255 0.90745
0.2000 0.00129 0.99871
0.3000 0.00000 1.00000

OC Curve for n=50, c=2

1.00

0.80
Probabilty of Acceptance, Pa

0.60

0.40

0.20

0.00
0.0000 0.0200 0.0400 0.0600 0.0800 0.1000 0.1200 0.1400 0.1600 0.1800 0.2000

Fraction defective, p
(b)
p = 0.1030 will be rejected about 90% of the time.

(c)
A zero-defects sampling plan, with acceptance number c = 0, will be extremely hard on the
vendor because the Pa is low even if the lot fraction defective is low. Generally, quality
improvement begins with the manufacturing process control, not the sampling plan.

You might also like