Documenti di Didattica
Documenti di Professioni
Documenti di Cultura
Allied Signal
Johnson & Johnson,
Ford, Nissan,
Motorola
General Electric Honeywell
Scientific:
• Structured approach. “Show me
• Assuming quantitative data. the data”
”Show me
the money” Practical:
• Emphasis on financial result.
• Start with the voice of the customer.
It is a Process
To achieve this level of
performance you need
It is a Philosophy to: Define, Measure,
Anything less than Analyse, Improve and
ideal is an opportunity Control
for improvement
Defects costs money
Understanding
processes and It is Statistics
improving them is the
most efficient way to 6 Sigma processes will
achieve lasting results produce less than 3.4
defects per million
opportunities
Philosophy
Know What’s
Important to the
Customer (CTQ)
Reduce Defects
(DPMO)
Center Around
Target (Mean)
Reduce Variation
(Standard Deviation)
Data Driven
Decision
Y= f(X)
• Y • X1 . . . Xn
• Dependent • Independent
• Input-Process
• Output • Cause
• Effect • Problem
• Symptom • Control
• Monitor
• Define • Define
• Measure • Measure
• Analyze
• Analyze • Design
• Improve • Verify
• Control
Where can Six Sigma be applied?
Service
Design
Management
Purchase
IT
Quality
Depart.
HRM M&S
Is Six Sigma New?
- More Setups
- Expediting Costs
Hidden Costs:
- Lost Sales - Intangible
- Late Delivery - Difficult to Measure
- Lost Customer Loyalty - Lost Opportunities
- Excess Inventory
- Long Cycle Times - The Hidden Factory
- Costly Engineering Changes
Target = µ
Statistical background
‘Control’ limits
+/ − 3 σ
Target = µ
Statistical background
Required Tolerance
LSL USL
+/ − 3 σ
Target = µ
Statistical background
Tolerance
LSL USL
+/ − 3 σ
Target = µ
+/ − 6 σ
Six-Sigma
Statistical background
Tolerance
LSL USL
+/ − 3 σ
1350 1350
ppm ppm
Target = µ
+/ − 6 σ
Statistical background
Tolerance
LSL USL
+/ − 3 σ
1350 1350
ppm ppm
0.001 0.001
ppm ppm
Target = µ
+/ − 6 σ
Statistical background
Tolerance
LSL USL
1. 5σ
3.4 66807
0 ppm ppm ppm 3.4
ppm
+/ − 6σ
Performance Standards
σ PPM Yield
2 308537 69.1%
3 66807 93.3%
4 6210 99.38% Current standard
5 233 99.977%
6 3.4 99.9997%
World Class
Centered
On-Target
Center Reduce
Process Spread
1. Process Power
2. People Power
Process Power
P-D-C-A
Act Plan
A P Plan the change
Act on what
was learned
Check C D Do
Check the results Implement the change on a
small scale.
DMAIC - simplified
• Define
– What is important?
• Measure
– How are we doing?
• Analyze
– What is wrong?
• Improve
– Fix what’s wrong
• Control
– Ensure gains are maintained to guarantee
performance
DMAIC approach
I
Improve Critical milestones and stakeholder review
C
Control Budget allocation
Define
Business Case Voice of the Customer
VOC Key Issue CTQ
Delighters
More Is Better
Must Be
CUSTOMERS
SUPPLIERS
Problem Statement:
Goal: Inputs Process Outputs
Business Case:
Scope: Yield: 60%
Cost Benefit Projection:
Milestones:
Yield: 90%
Yield: 45%
Yield: 98%
Example - SIPOC
A SIPOC will allow your project team to put parameters around
the process being reviewed and identify the areas impacted
both up and down stream
SIPOC
Suppliers Input Process Output Customer
Clients Requirements Profile Client
Sales People Resumes Interview Summaries Sales People
Candidates Profiles Offer Letters Delivery Management
Web Site Margin Template Candidate/Employee
Recruiting Data Base
M
Measure
C
Control Collect data
Measure
Identify the Metrics Identify Process Capability Display Data
LSL USL 1000
UCL
Cp = 0.4
I P O s = 2.7
0
X
-1000 LCL
10 20 30 D B F A C E Other
Measure
the
process
Validate Measurement
Prioritize the Metrics Data Collection Plan Systems
Data Collection Plan Col # 1 2 3 4 5 6
O1 O2 O3 O4 What questions do you want to answer? Inspector A B
Sample # 1st Trial 2nd Trial Diff 1st Trial 2nd Trial Diff
I1 Data Operational Definition and Procedures
1 2.0 1.0 1.0 1.5 1.5 0.0
I2 FMEA What Measure type/ How Related Sampling How/ 2 2.0 3.0 1.0 2.5 2.5 0.0
I3 Data type measured conditions notes where 3 1.5 1.0 0.5 2.0 1.5 0.5
4 3.0 3.0 0.0 2.0 2.5 0.5
I4 5 2.0 1.5 0.5 1.5 0.5 1.0
Totals 10.5 9.5 3.0 9.5 8.5 2.0
Averages 2.1 1.9 0.6 1.9 1.7 0.4
How will you ensure What is your plan for Sum 4.0 Sum 3.6
consistency and stability? starting data collection? R 1.8 R
XA 2.0 A XB B
How will the data be displayed?
Analyze
D
Define
How well or poorly processes are working
compared with
M - Best possible (Benchmarking)
Measure - Competitor’s
C
Control
Analyze
Process Door Data Door
VA NVA 22 O O
21 O
n
O
n O n
O
n
18 X O X n X
17 n O n
X
16 n X O
15 X n X
14 X n
13 X
12
1 2 3 4 5 6 7 8 9 10
.
Chi-Square t-test
c² ANOVA
Y Regression Analysis
Regression
X1
.
.
Improve
C 3 G
E
D
D 2 H
G
I J
Perform
Cost-Benefit Run Pilot
Full scale
Analysis Original
Test
Assess Risks
Select the Solution FMEA
Control
M
Measure
A
Analyze How will you maintain to gains made?
QC Process Chart
Date of Issue: Issued by: Approved by:
Process
Revision Date Reason Signature
Product Name
Process Name
Process Code #
Results
1
12
Ownership &
Monitoring Process Change s =
Cp =
3.7
1.4 LSL
s = 2.7
Cp = 0.4
USL
Management
Before After
UCL } Improvement
A1 A2 A3 A4 A2 A1 A3 A4
Before After Good
} Improvement
} Remaining Gap
Green Belts
Yellow Yellow
Belt Belt
Yellow Yellow
Belt Belt
Champion
External Sources:
Voice of Customer
What are we falling short of meeting customer needs?
What are the new needs of customers?
Voice of Market
What are market trends, and are we ready to adapt?
Voice of Competitors
What are we behind our competitors?
Sources of Projects
Cont.
Internal Sources:
Voice of Process
Where are the defects, repairs, reworks?
What are the major delays?
What are the major wastes?
Voice of Employee
What concerns or ideas have employees or managers
raised?
What are we behind our competitors?
Project Selection