a design of inspection sampling plans for incoming ... · a design of inspection sampling plans for...
TRANSCRIPT
. . 2556
16-18 2556
A Design of Inspection Sampling Plans for Incoming Aluminum Parts
1*, 2 1,2 . 20130,
E-mail: [email protected]*
Banhan Lila1* Jakrawarn Kunadilok2
1,2Department of Industrial Engineering, Faculty of Engineering, Burapha University, Chonburi
E-mail: [email protected]*
MIL STD 105E Visual C++
32.53% 82.08% 7.20% 0.99%
682,000
Abstract
Quality of parts is a significant factor affecting the subsequence operations. The acceptable performance
of an incoming inspection with reasonable cost is required. This paper presents a design and an
implementation of the inspection plans for incoming aluminum parts of a safety belt production process. The decision support system written in C++ were designed and used for inspecting of attribute quality
characteristics. The application in the screening process indicated that 82.08% of defectives were found at the incoming inspection station compared to only 32.53% previously. This improvement resulted in the
reduction of the leakages of defective parts into the production process from 7.20% to 0.99%. Consequently, cost related to the quality problem was decreased by the average of 682,000 baht per
month which could be viewed as a solid evidence and a guideline for implementation such techniques in the similar situations.
Keywords: Inspection Plan, Aluminum Parts, Decision Support System
. . 2556
16-18 2556
1.
[5] William Cooper
Proctor Procter & Gamble
. . 1887 �
�
Production and Operations
Management Roger, Kevin, and Dongli [6]
TQM
[6] [7]
[1],
[2] [3]
(Inspection) Mistake-Proofing, 100%
(Sampling Inspection) (SPC)
Mistake-Proofing Poka-Yoke Go-
NoGo gages
(Acceptance Sampling Plan)
MIL-STD 105D, MIL-STD 105E
American Society of Quality Control (ASQC) ANSI/ASQC Z1.4 [8] [9]
[1], [2]
[3]
MIL-STD 105E
[1], [2], [3] [4]
(Producer�s
Risk, ) (Consumer�s Risk, )
MIL STD 105E Visual C++
MS Excel
,
(Average
Outgoing Quality, AOQ) (Average Total Inspection, ATI)
2.
(Incoming Materials) (Work in Process)
(Outgoing Products) [9]
(Lot)
. . 2556
16-18 2556
(Accept) (Reject)
( Lot-
Disposition Action)
(Single Sampling Plan, SSP) (Double-Sampling Plan, DSP) (Multiple-
Sampling Plan, MSP) (Sequential-
Sampling Plan)
, 2550 [1]
CKD
, 2550 [2]
MIL-STD-105E
, 2552 [3] Poka-Yoke
MIL-STD-105E
, . 2552, [4]
Marvin, Kim, and Park, 2009 [7]
Belmiro and Pedro, 2008 [8]
SSP DSP
Andreas et al,
2011 [10]
Escherchia coli O157
Vellaisamy, Sankar and Taniguchi, 2003 [11] Aminzadeh, 2008 [14]
(Autoregressive
Moving Average, ARMA) [11] DSP [14]
Muhammad, 2011 [12] Pearn and Chien-Wei, 2006 [13]
[12]
EOQ [13]
. . 2556
16-18 2556
3.
MIL-STD-105E
3.1
MIL STD 105E Visual C++
MS Excel
Acceptable Quality Level (AOQ) 0.1% 10%, Lot Size (N),
(Continuous Isolated), ( SSP, DSM MSP)
(General I - III Special
I - IV) C++ MS DOS 1
1 C++
Notepad
(n) (c Ac) MS Excel 2007 2
2 MS Excel 2007
OC Curve, AOQ, AOQL,
ATI ASN
3.2
MIL-STD-105E
Notepad C++
3.3
30
4.
4
[3]
1 669
731 1400 (
) 47.8 3
1
P 5800 158 0.699 68 0.301
M 2500 144 0.735 52 0.265
A 7500 259 0.325 537 0.675
AY 3950 108 0.593 74 0.407 : A = M = A =
AY =
300
. . 2556
16-18 2556
7500 259 796
32.53 1
3.9, 7.8, 10.6 4.6
3
537
67.5
3
4
4 ( ) ( )
2 POKA-YOKE
1 Coordination Measuring (CMM)
n=5 (c=0)
1 (p) 0.106
Pa (1) AOQ (2) ATI (3)
Pa = 0.57, AOQ = 0.06 ATI = 132 3
57
1 67.5
(1)
(2)
(3)
d c n
N p
AOQ = 0.06
6 7500
446 ( 1 537 )
132
(1)
(OC Curve) AOQ ATI 5, 6 7
n=5 c=0
MIL-STD-105E
Pa, AOQ, ATI
. . 2556
16-18 2556
5 OC n=5, c=0
6 AOQ N=300, n=5, c=0
7 ATI N=300, n=5, c=0
5.
2 1
2
General Level I, II III Nornal, Tightened Reduced AQL= 1%
2
2
I II III
F H J
Normal 20/0 50/1 80/2
Tightened 20/0 80/1 125/2
Reduced 5/0 20/1 50/1
2 20/0
Normal I n=20, c=0
n=5 c=0 Reduced
(Switching Rule) [8] Normal 3
8, 9 10
8 OC
9 AOQ
. . 2556
16-18 2556
10 ATI
8, 9 10
Normal N= 300
n/c 20/0, 50/1 80/2 8 9 10
3
3
I II III
0.106 0.026 0.007
AOQ 0.056 0.050 0.044
ATI 140 157 174
I
n=20 c=0
0.106
AOQ 3
10
6.
n=20, c=0
10 3126 Reject 7 142
100%
31
10 173
(p) 0.055 (0.106)
82.08
0.99
32.53 82.08
7.2 0.99
n=20, c=0
(p)
0.106 0.055
p = 0.106
p = 0.055
AQL=1%
Normal Reduced
AQL
7.
MIL-STD-105E
682,000 [3]
. . 2556
16-18 2556
2552 57/2552
[1] . 2550.
(CKD). ,
, , . [2] . 2550.
MIL-STD-100E.
, ,
, . [3] . 2552.
.
, , 21-22 2552: .
[4] , . 2552.
MIL-STD-105E. ,
, ,
, 40-55. [5] James R.E. and William M.L. 2005. The
Management and Control of Quality, Thomson South-Western, Singapore; 3-4.
[6] Roger S., Kevin L., and Dongli Z. 2005. Evolution of Quality: First Fifty Issues of
Production and Operations Management. Production and Operations Management, Vol. 14,
No.4 : 468-481.
[7] Marvin R., Kim D., and Park E. 2009. A Sampling Policy for the Reduction of Quality
Cost and Improvement of Accepted Percentage
in Company L. The Asian Journal on Quality, Vol. 10, No. 3 : 99-113.
[8] Belmiro P. and Pedro M. 2008. An Optimization-Based Approach for Designing Attribute
Acceptance Sampling Plans. International Journal of Quality & Reliability Management,
Vol. 25, No. 8 : 824-841. [9] Douglas C. M. 2005. Introduction to Statistical
Quality Control (5th ed.). John Wiley
International, U.S.A : 646-709. [10] Andreas K., Glen M., Robert B. and IAN J.
2011. Assumptions of Acceptance Sampling and the Implications for Lot Contamination:
Escherichia coli O157 in Lots of Australian Manufacturing Beef. Journal of Food Protection,
Vol. 74, No. 4 : 539-544.
[11] Vellaisamy P., Sankar S. and Taniguchi M. 2003. Estimation and Design of Sampling Plans
for Monitoring Dependent Production Processes. Methodology and Computing in Applied
Probability, Vol. 5, No.1 : 85-108. [12] Muhammad A.. 2011. Economic Order Quantity
with Imperfect Quality, Destructive Testing Acceptance Sampling, and Inspection Errors.
Advances in Management & Applied Economics,
Vol.1, no.2 : 59-75. [13] Pearn WL. and Chien-Wei W. 2006. Variables
Sampling Plans with PPM Fraction of Defectives and Process Loss Consideration. Journal of the
Operational Research Society, Vol.57: 450-459. [14] Aminzadeh M. S. 2008. Sequential and Non-
Sequential Acceptance Sampling Plans for
Autocorrelated Processes using ARMA(p,q) Models. Comput Stat, Vol.24 : 95-111.