Vous êtes sur la page 1sur 10

EXPERT SYSTEM FOR FLEXIBLE

MANUFACTURING SYSTEM

Ashraf S. Youssef; Ph. D.

Agenda
„ Thesis Objective & Scope.
„ Motivation.
„ Why Flexible Manufacturing System?
„ QCES Parameters & Assumptions.
Assumptions
„ QCES: A Framework for KB- DSS.
„ Why Control Chart Patterns?
„ Control Charts Patterns Identification Techniques.
„ Pattern Identification Attributes (Features).
„ The Computer Program (Analytical Part).
„ QCES Rule-Base Building.
„ CASE STUDIES.

Thesis Objective & Scope

„ The main purpose of the current research work is to


propose a conceptual framework for an online real
time quality control system matching with the features
and requirements of the recent advances in
manufacturing systems, especially Flexible
Manufacturing Systems (FMS). According to the
proposed framework, an online expert quality control
system (EQCS) is developed and implemented.

1
Motivation
„ To date, quality control methods remain underutilized.
„ Expertise is needed in quality control.
„ Application
pp of Expert
p System
y ((ES)) in q
qualityy control
activities is important in FMS.
„ Most of the research efforts focus on obtaining good rules to
help construct good quality control diagnostic system.
„ Most of the recent research suggests a framework of ES to
develop statistical process control applications.

Motivation (Cont.)
„ Most applications of ES in manufacturing concluded that
the ES technology allows for implementation of
sophisticated and efficient process control systems.
„ The new philosophy of manufacturing control became in
demand when FMSs were installed.
„ All researchers that discussed pattern recognition
concentrated on only six patterns: systematic, trends
(upward & downward), stratification, cyclic, and natural
pattern.

Why Flexible Manufacturing


System?

Produce Different Products


in Small Batches

Fully
Automated FMS Costly
System

Utilize Advanced
Technology

2
QCES Parameters &
Assumptions
„ QCES is concerned with the analysis of control charts
for variables (X-bar and R charts).
„ QCES is based on the 3 sigma limits.
„ I t
Interpretation
t ti ini QCES ddepends d on th
the AT&T rules
l
and on the identification of the chart pattern.
„ QCES identified the last six patterns as unknown.
„ Attribute-value triple mode was used to represent the
knowledge base of the ES part.
„ Production rule was used to build the rule base.

QCES: A Framework for


KB- DSS
ES Part
Pattern Identification (computer program)

Knowledge Model Base Statistical


Process Patterns
Base I Analysis
Information Information

QCS
Inference
Characteristics
Engine
Computations

Input Data

User
Interface

Why Control Chart


Patterns?
„ Non-random patterns in control charts signal the presence
of special or assignable causes even if all points fall
within the control limits.

„ Correct interpretation of patterns helps the quality


professional in identifying assignable causes; Western
and Electric Company stated fourteen unnatural patterns
of control charts and the common causes of each pattern.

3
Control Charts Patterns
Identification Techniques
„ Work on patterns identification in quality control charts
have taken four main directions:
„ Expert System. (QE Interpretation)
„ Computer Vision. (QE Interpretation)
„ Neural Network. (Time & Effort)
„ Feature-Based Method.(More Accurate)

„ Feature-based method is the most accurate. Pham and


Wani (1997) stated that this has 99% accuracy for pattern
recognition.

Control Chart Pattern


Identification procedure
Investigate the Patterns and Extract the
Features

B ild a Database
Build D t b

Convert these Data into a Decision Tree

Develop Computer Program

Verify the Results

Pattern Identification
Attributes (Features)
„ Test of normality
„ Slope
„ Moving Average
„ Xi>Xi+1 and Xi+1<Xi+2 for all samples
„ 9 points Consecutive above CL or lower CL
„ 9 points Consecutive below CL + σ
„ 8 of points Lie on warring Limits Zone
„ Points > 5 σ + CL
„ 15 Points consecutive in Zone C

4
Decision Tree of the
Pattern Identification
SQC
Chart

Test of Normality

Fail Pass
Moving Average
Normal
Increased
Decreased Pattern
Increasing Others
Trend Decreasing
Xi>Xi+1 and Xi+1 < Xi+2 Trend
For all Xi’s

Pass
Fail

Systematic X i > X + 2σ or
Pattern
X i < X − 2σ
p = 8 points
Fail
Pass

Mixture
X i < X − 1σ or X i > X + 1σ
p = 1 5 points

Decision Tree of the Pattern


Identification (Cont.)
Fail
Pass

Startis-
fication More than one point
>5σ

Fail Pass

9 Consecutive Points
Freaks < X − 2σ

Fail Pass

Sudden Shift
in level 9 Consecutive Points >
X + σ or > X − σ

Fail Pass

Unknown
Gradual Pattern
Change

The Computer Program


(Analytical Part)
„ A computer program was developed based on the VB
language; the program includes the following activities:
„ Computation of the quality control chart characteristics (X-bar
and R charts).
„ Plotting the quality control charts.
„ Computation of the process capability.
„ Interpretation of the quality control charts by applying AT&T
rules first and then applying pattern identification procedure.
„ Identification of the process status i.e. in or out of control &
why?

5
QCES Rule-Base Building
Collect data (assignable causes) related
to the unusual patterns

Construct an attribute value table

Develop a rule-base

Develop computer program

Verify rule-base

CASE STUDIES

„ Three case studies were considered to verify the


proposed EQCS framework:
„ Case Study I (From Statistical Quality Control Hand
Book)
„ Case Study II (Conventional M/C)
„ Case Study III (FMS)

CASE STUDY I
(SQC Handbook)
Samp Sample Size
le No. 1 2 3 4 5
1 11.1 9.4 11.2 10.4 10.1
2 9.6 10.8 10.1 10.8 11.0
3 9.7 10.0 10.0 9.8 10.4
4 10.1 8.4 10.2 9.4 11.0
5 12.4 10.0 10.7 10.1 11.3
6 10 1
10.1 10 2
10.2 10 2
10.2 11 2
11.2 10 1
10.1
7 11.0 11.5 11.3 11.0 11.3
8 11.2 10.0 10.9 11.2 11.0
9 10.6 10.4 10.5 10.5 10.9
10 8.3 10.2 9.8 9.5 9.8
11 10.6 9.9 10.7 10.2 11.4
12 10.8 10.2 10.5 8.4 9.9
13 10.7 10.7 10.8 8.6 11.4
14 11.3 11.4 10.4 10.6 11.1
15 11.4 11.2 11.4 10.1 11.6
16 10.1 10.1 9.7 9.8 10.5
17 10.7 12.8 11.2 11.2 11.3
18 11.9 11.9 11.6 12.4 11.4
19 10.8 12.1 11.8 9.4 11.6
20 12.4 11.1 10.8 11.0 11.9

6
CASE STUDY I
(Computer Implementation)

CASE STUDY I
(Consultation Session)

CASE STUDY II
(Conventional M/C)

7
CASE STUDY II
(Computer Implementation)

CASE STUDY II
(Consultation Session)
2.50
2.00
1.50
1.00
0.50
0.00
Z
(

-0.50 0 0.5 1 1.5


-1.00
-1.50
1 50
-2.00
-2.50
R ( i )

CASE STUDY III


(FMS)

8
CASE STUDY III
(Computer Implementation)

CASE STUDY III


(Consultation Session)

DISCUSSION
Case Study I
Item R Chart X-bar Chart
Case Study III
Center line No Difference No Difference Item R Chart X-bar Chart

Upper Control No Difference No Difference


Center line No Difference No Difference
Limits
Lower Control No Difference No Difference
Limits Upper Control No Difference No Difference
Limits
Case Study II
Lower Control No Difference No Difference
Item R Chart X-bar Chart Limits

Center line No Difference No Difference

Upper Control 0.003mm -0.002mm


Limits
Lower Control No Difference 0.003mm
Limits

9
DISCUSSION (Cont.)
„ Three case studies were used for verification.
„ In Case Study II, the causes of out-of-control were fired as
follows: rotation of fixture, tool in need of sharpening,
wear off tool,
l use off defective
d f i raw materials,i l andd machine
hi
in need of repair.
„ There is no significant difference in the results of the
characteristics of the control charts.
„ The normality test was also performed to verify the EQCS
decisions.

Conclusion
„ In this research, a quality control expert system (QCES)
framework was developed. This framework integrates
statistical quality control system with expert system
((Hybrid
y DSS).) The pproposed
p framework:
„ Allows for the identification of instability patterns of control
charts.
„ Helps to develop an on-line statistical quality control and process
diagnostic system for FMS.
„ Makes on-line quality control and adaptive sampling plans more
effective in FMS.
„ Was applied and verified in three different case studies.

Thank You

10