1. An Introduction to Six Sigma
School of Manufacturing Engineering
PT D155 – Quality Control
April 15, 2014

2. ‘Six Sigma’ Experiences and Leadership
Companies who have successfully adopted ‘Six Sigma’ strategies include:

3. General Electric - Example
In 1995 GE mandated each employee to work towards achieving 6 sigma
The average process at GE was 3 sigma in 1995
In 1997 the average reached 3.5 sigma
GE’s goal was to reach 6 sigma by 2001
Investments in 6 sigma training and projects reached 45MUS$ in 1998, profits increased by 1.2BUS$
“the most important initiative GE has ever undertaken”.
Jack Welch
Chief Executive Officer
General Electric

4. Chairman of the Executive Committee
Motorola
“At Motorola we use statistical methods daily throughout all of our disciplines to synthesize an abundance of data to derive concrete actions….
How has the use of statistical methods within Motorola Six Sigma initiative, across disciplines, contributed to our growth? Over the past decade we have reduced in-process defects by over 300 fold, which has resulted in cumulative manufacturing cost savings of over 11 billion dollars”*.
Robert W. Galvin
Chairman of the Executive Committee
Motorola, Inc.
*From the forward to MODERN INDUSTRIAL STATISTICS by Kenett and Zacks, Duxbury, 1998

5. Kodak

6. Kodak

7. Linkage of 6s to financial performance
Financial Aspects
Linkage of 6s to financial performance

8. Six Sigma Framework

9. Six Sigma Black Belt Resources
Training in Six Sigma methods.
Blackbelt- 20 days
Green Belts-10 days
Time commitment to carry out the project !
Availability of softwares to facilitate data analysis.
Blackbelts roles as change agents and project leader!
Coaching by assigned champions or external consultants.

10. Champions, ‘Enablers’, or change agent
High-level managers who champion Six Sigma projects
They required support from an executive management committee
Orchestrate the work of Six Sigma Black Belts
Provide Black Belts with the necessary backing at the executive level

11. Top Level Management Commitment
Six Sigma practitioners who are employed by the company using the Six Sigma methodology
Work full time on the implementation of problem solving & statistical techniques through projects selected on business needs
Become recognised ‘Black Belts’ after embarking on Six Sigma training programme and completion of at least two projects which have a significant impact on the ‘bottom-line’

12. Further down the line - after initial Six Sigma implementation package
Master Black Belts
Black Belts who have reached an acquired level of statistical and technical competence
Provide expert advice to Black Belts
Green Belts
Provide assistance to Black Belts in Six Sigma projects
Undergo only two weeks of statistical and problem solving training

13. Six-Sigma - A “Roadmap” for improvement

14. Formalised Methodology : DMAIC Process
Five phase D-M-A-I-C technique used as a breakthrough strategy in manufacturing process that enables real improvement and results that meet the needs of the customer.
By defining, measuring, analyzing, improving and controlling the Critical To Quality (CTQ) factors , make it possible to roll up the individual performance indicators into one aggregate value that will indicate the overall improvement of the organization

15. Improvement to Existing Processes
DMAIC
Define
Select a project and identify process or products
Measure
Prepare for assimilating information such as specify CTQs, evaluate measurement, estimate process capability
Analyze
Characterise the current situation – determine the root causes of defects
Improve
Optimize the process – implement changes to improve process performance
Control
Assure the improvements – develop system to maintain the improved process

16. Key Deliverables Define Measure Analyze Improve Control
DMAIC
Define
Charter created for all the relevant metrics, scope of the project), relevant team members from cross functional depts.
Measure
GR&R, Cpk , QFD can also be used to refine and validate the output metrics -referred to as CTQs. GR&R studies evaluate the ability to replicate results (Repeatability) when multiple measurements are taken on the same units by three (max) operators .(Reproducibility)
Analyze
Critical X’s identified, FMEAs and data collected and analysed for key process , input and output variable. Data is analyzed with statistical softwares to identify variable having the most significant impact on the output variables.
Improve
Demonstrated improvement –using problem solving techniques to address the root causes and measures for improvement on performance of the process – each process change is tested with a confirmation study . DOE & FMEA , FTA and 8Ds can be helpful in these instances.
Control
Control plan- to ensure improved performance of the process is sustained after the six sigma team has completed its work and moved on to another project – the key tools of this phase are SPC charts

17. Define Measure Control Analyze Improve
Six Sigma Tools
DMAIC
Define
Charters
Project Management
Measure
QFD
GR&R
C&E
Control
SPC Charts
Capability Studies
Control plans of processes
Analyze
Process Maps Multi-vari charts
FMEA
Pareto, Control Charts, Capability Studies
Improve
DOE
Pilot Runs on Products

18. Basic QC and Six Sigma Tools
Types of Variation
Inherent or Natural variation
Due to the cumulative effect of many some unavoidable causes
A process operating with only chance causes of variation present is said to be “in statistical control”
Assignable causes variation
Assignable from external factors which give rise to sporadic effect of the process.
Assignable causes of variation can be easily identifiable e.g. changes of shift or operator.

19. Types of Variation Inherent or Natural variation Disturbed process
Temporary upsets
Natural process
Natural boundary
Natural boundary

20. Common Causes Examples
Poor design due to inherent features
Poor maintenance of machines due to non replacable parts
Unclear standard operating procedures (SOPs) caused by frequent changes
Of product to keep up with technology (e.g . Hard drives)
Poor working conditions (e.g. lighting, noise, dirt, ventilation)
Low yield raw materials ( wafer fabrication in IC industries)
Vibration in industrial processes
Ambient temperature and humidity caused by location
Normal wear and tear of machinery parts
Variability in settings due to drifting of parameters
Computer response time due to usage

21. Special or Assignable Cause
May be due to:
Improperly adjusted machine
Operator error
Defective raw material
Broken part
Equipment malfunction
Inappropriate procedures

22. Example of special cause variation
A process operating in the presence of assignable causes of variation look like as follows :
e.g. An upward drift of the process above the average

23. Case Study 1: Effectiveness on Inspection process
1. Count the number of “F & f ” in the passage:

24. 2. Count the number “X” in the passage below
to get the correct answer of exercise 1

25. PPM, DPMO, DPU, DPO
The number of defectives per million inspected items (ppm)
Defects per unit (DPU) = Total defect observed
Total number of units produced
Defect per unit opportunity (DPO):
DPO = DPU m
where m is the number of opportunities for error
(d) The number of defects per million opportunities (DPMO) used in the service industries.
DPMO = DPO x 10^ 6

26. Case Study 2: A football game
The process of a football can be defined as the kick of a field goal from the snap of the ball to the whistle is blown by the referee at the completion of a play. Each time a field goal is attempted , a unit is produced. There is one type of defect in the process is a missed field goal. Even though there is one type of defect which could occur in the process , there are eleven opportunities during the process where an error can occur. i.e there are 11 players to a team. During the football season a kicker attempts 27 field goals and two attempts failed due to one bad snap and one inaccurate kick .
1. What is the Defect per unit (DPU) by the kicker?
2. What is the Defect Per Opportunities (DPO) by each player?
3. What is the Defect Per Million Opportunities (DPMO) for error?
4. What is the DPO when there are 9 players left when two of them are injured and the team still plays on. ?

27. Measurement of Process Variation
Variation is inevitable because a process contains many sources of variability. The measures may be large or small but are always present.
The variation, if the data values are measured and plotted, can be visualised by means of a distribution called a bell-shaped ( Gaussian) curve. This distribution can be characterised by:
Location ( Average)
Spread (Range)
Shape (Skewed , symmetrical)

28. Measurement of Process Variation
Variation constituted a major cause of defectives and is a key element in the process improvement
Variation related to how close are the measured values to the target value, cycle time to how fast,
and yield to how much.
Cycle time and yield are major elements of productivity

29. Process Variation –not so good
Natural data spread
Process is two sigma, that means the amount of variation covered by two standard deviations
-3
-2
-1 
+1
+2
+3
68%
95%
99.7%
Simple bell-curve distribution with 68%, 95% and 99.7% population with sigma limits 1, 2, and 3

30. Measurement of Process Performance
With a simple set of lines known as ‘sigma limits’ , the engineer can visualize and understand how a process is performing-keeping the process between lines.
A normal bell-shape curve represents 100% of the parts being measured. If the bell shape curve is non normal or irregular it represents existence of special cause for the variation in process data. The lesser the variation the better is the use of six-sigma tools.

31. Measurement of Process Performance
Process has to be in a relative process control before applying six-sigma.
If all parts fall under a normal-bell-shaped curve and within three sigma limits on each side of the process average (+3σ and -3σ within customer specification ). Then only 3.4 defects ( DPMO) would be produced for every million opportunities levels.
The process is operating at six-sigma performance levels which is the goal .

32. Six Sigma Quality Level
By dividing the scale into three sections from the specification center (i.e. target), a level of confidence can be established for how consistently the product values can be maintained with respect to the customer specs over time.
Process can be adjusted if sigma limits indicate process shift.
The greater percentage of the parts or process being measured fall closest to the target indicates process is more capable of producing parts with lesser variation.

33. The sigma limit is calculated using the following equation:
Six Sigma Basics
Six Sigma Objective
The objective of six-sigma is to make sure that sigma – the standard deviation of a process – is as small(narrow) as possible, indicating the least amount of variation.
The sigma limit is calculated using the following equation:
n : No. of sample values
x : individual value
S =   ( x 2 ) - ( x ) 2 / n ]
 [ n-1 ]

34. Calculating Sigma Limits
Case study 3
A small manufacturing company that makes cement building blocks. Each block is supposed to weigh 20lb, but due to variation in the amount of water, drying time and mixture etc., some of the blocks weigh more and some weigh less. The blocks can weigh as much as 27lb and as little 13lb. If they are greater than the upper limit of 25lb or below the lower limit of 15lb, then they are considered unacceptable and scrapped.
To find the sigma for this process, five cement blocks weights. Xs: 21.0 , 22.0 ,19.0 , 20.0 , 19.0

35. Performance Standards
PPM
Yield 2 3 4 5 6
308537
66807
6210
233
3.4
69.1%
93.3%
99.38%
99.977% %
Current standard
World Class
Process
performance
Defects per
million
Long term
yield

36. Performance standards First Time Yield % at Multiple stages process
Number of processes 3σ 4σ 5σ 6σ 1 10
100
500
1000
2000
2955
93.32
50.09
0.1
99.379
93.96
53.64
4.44
0.2
99.77
97.70
89.02
79.24
62.75
50.27
99.966
99.83
99.66
99.32
99.0

37. Six Sigma and other Management Initiatives
SPC
GMP
TPS
SPC
Problem
Solving teams
Improvement teams
Problem
Solving teams GT
Improvement teams
Quality Awards
Strategic
planning
Strategic
planning
Knowledge
Management
Knowledge
Management
ISO 9000
ISO 9000
ISO 14000
JIT
DOE
Benchmarking
DOE
and more
Benchmarking
and more

38. Overview of the Key Six Sigma Tools
Process Maps – A schematic flow of a process showing process inputs, steps and o outputs
Cause and Effect Matrix- A “ L Shape” matrix that enables the six sigma implementer to prioritise and select those process input variables (Xs) that have the greatest effect on the process output variables (Ys) for improvement purpose.
Measurement System Analysis– A study of the measurement system using Gage R&R methodology to quantify the measurement repeatability and reproducibility.

39. Overview of the Key Six Sigma Tools
Process Capability Study- Analysis of process variation versus process specifications to assess the ability of the process to meet the specifications.
Failure Mode and Effect Analysis– analytical approach for identifying potential process problems by prioritizing risk based on severity of failure modes, causes occurrences and ease of detection of problem for improvement action.
Multi-vari study- a study that samples the process as it operates by statistical and graphical analysis . It identifies the important controlled and uncontrolled (noise) variables into positional , cyclic and temporal variation.

40. Overview of the Key Six Sigm Tools
Design of experiments – a method of experimentation that identifies, with minimum testing, how key process input variables affect the output of the process.
Control Plan- document that summarizes the results of a six sigma project and aids the operator in controlling the process.

41. Linkage of Six Sigma to other existing Quality Management Systems
Six Sigma is a methodology for making a break through process improvement. It is not a system for managing quality in an ongoing manner. It is not intended to define the proper criteria for world-class quality management
Normally an organisation will implement a Quality management System based on ISO 9000 or Malcomb Bald ridge. (e.g. ISO9000 for European community ).
ISO 9000 compliance provide a means to the six sigma implementation

42. Linkage of Six Sigma to other existing Quality Management Systems
ISO 9000 compliance required the documentation of the methodology used when six sigma is implemented .
The quality system audits and other ISO infrastructure ensures compliance to the documentation of the six sigma process.
Six sigma is a approach for succeeding in many of the Baldridge criteria, such as tangible business results

43. Limitations of Six Sigma
Not a provision on template for evaluating an organization’s overall quality management efforts
Does not dictate on quality policy
Does not provide strategies for working with suppliers
Does not mention human relations and quality auditing,
Six sigma is project oriented and not quality management system as a whole. There is a need for deployment and development of overall quality policy and ongoing quality systems to ensure their implementation.

44. Integration of Six Sigma with TQM
Some of the elements in a Total Quality Management program are found in Six sigma Practices:
Customers orientation and focus
Work as a form of process flow
Instill a continuous improvement mindset
A goal for improvement of all aspects and functions of the organization
Decision making from data base
The use of statistical methods across the board.
In Summary, six sigma can be integrated with existing quality management systems.

45. Contrasts between Six Sigma and TQM
TQM attributes:
Led by middle level managers
Not directed at achieving tangible, budgeted results
Did not obtain the services of the top talent
Lack formal processes for project selection and review
Lacked financial scrutiny to budget for and validate financial savings
Did not have well defined roles
Was implemented with part time resources
In Summary, the DMAIC road map has been a huge break through for six sigma but this approach is missing in most of the TQM implementations.

46. Benefits of Six Sigma
Dramatically lower costs
Improve customer satisfaction
Shorten time to market
Reduce defects, scrap and re-work
Simplify operations
Improve competitive position
Repeated application of strategy to individual projects
Projects selected that will have a substantial impact on the ‘bottom line’

47. The Six Sigma Principles
Focus on the customer
Continuous process improvement
Leading by example
Company wide implementation
Business strategy integration
Decision making using statistical analysis

48. Six sigma a Structured Approach
A scientific and practical method to achieve improvements in a company
Scientific:
Structured approach.
Assuming quantitative data.
Practical:
Emphasis on financial result.
Start with the voice of the customer.
“Show me
the data”
”Show me
the money”

49. Application of Six Sigma within an organisation
Service
Design
Management
Purchase
Six Sigma Methods
Administration
Production IT
Quality
Depart.
Human
Resource
M & S

50. References
Ronald D. Snee and Roger W. Horel., Leading Six Sigma A step-by-step Guide Based on Experience with GE and other Six Sigma Companies, Prentice Hall, 2003.
Gary Cornner.,Six Sigma and other Continuous Improvement Tools for the Small Shop, Society of Manufacturing Engineers(SME), 2002.
INDUSTRIAL STATISTICS RESEARCH UNIT (ISRU), School of Mechanical and Systems Engineering, University of Newcastle upon Tyne, England
From the forward to MODERN INDUSTRIAL STATISTICS by Kenett and Zacks, Duxbury, 1998
Adapted from Zinkgraf (1999), Sigma Breakthrough Technologies Inc., Austin, TX.
Schaffer and Thomson,Harvard Business Review (1992)
Reference: Schaffer and Thomson, HBR, Jan-Feb. 1992
General Electric (GE), MOTOROLA, KODAK,
5/7/2019

51. Thanks !
5/7/2019

52. Team Assignment Given the cases below:
Over one month period , 46 preflight inspectors were informed with 26 defects noted by QA. The preflight has 67 items that are checked on each inspection.
Over last year , 1050 injections have been given by the hospital. In one instance the incorrect amount was administered and in another , the wrong drug was given. Considered amount and type of drug to be the only opportunity for error.
In the transportation section, main tires are checked for proper inflation prior to sending the vehicle out on the road. In the last month , 35 vehicles were sent out and on 3 occasions the pressure was incorrect.
5/7/2019

53. Team Assignment For each of the above case. a) Defining the defect ,
b) Identify the number of defect s,
c) What is the unit of defect
d) The number of units
Estimate:
The opportunities for error
DPU
DPMO
5/7/2019

54. Solution to Case Study 2 DPU = # of defects = 2 = 0.074 # of units 27
DPO = DPU = =
Opp for Error
DPMO = DPU x = x =
# Opp for Error
5/7/2019

55. Solution to Case Study 3 Target : 20 Process average : 20.2 USL : 25
LSL: 15
Process Spread : 13 to 27
Cp = (USL-LSL) = =
Process spread 14
2. k = | Target- Process Ave.| = | | = 0.04
0.5 x( USL-LSL) ( 10)
Cpk = Cp x ( 1-k) = x (1-0.04) =
4. Sigma level = 3 x Cpk = 3 x = (i.e.1.5 shift)
5/7/2019

56. Solutions to Assignment
Case 1
Defect: Worn part being missed on inspection
# defect: 26
# units : each inspection 46
Opp. for error : 67 inspections
DPU = # of defects = =
# of units
DPMO = DPU x = x =
# Opp for Error
5/7/2019

57. Solutions to Assignment
Case 2
Defect: Incorrect amount, incorrect drug
# defect: 2
# units : each inspection 1050
Opp. for error : 2
DPU = # of defects = =
# of units
DPMO = DPU x = x = 650
# Opp for Error
5/7/2019

58. Solutions to Assignment
Case 3
Defect: Low Pressure
# defect: 3
# units : each check 35
Opp. for error : 4 tyres
DPU = # of defects = =
# of units
DPMO = DPU x = x =
# Opp for Error
5/7/2019