Six Sigma March 10, 2010 Confidential | Six Sigma 76 /87 S S i i x x S S i i g g m m a a – – G G r r e e e e n n B B e e l l t t T T r r a a i i n n i i n n g g Ver 1.0 eXel Solutions R.T. Nagar, Bangalore – 560032 www.exelsolution.com Copyright and Confidentiality Notice All rights reserved. These materials are confidential. This document is being submitted with the explicit understanding that no part of these materials would be reproduced or published in any form or through any means whether electronic, mechanical, photocopying or with the aid of any information storage or retrieval system, nor would the materials be disclosed to third parties without the express and prior written authorization of eXel Solutions.
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Six Sigma March 10, 2010
Confidential | Six Sigma 76 /87
SSiixx SSiiggmmaa –– GGrreeeenn BBeelltt
TTrraaiinniinngg
Ver 1.0
eXel Solutions R.T. Nagar, Bangalore – 560032
www.exelsolution.com
Copyright and Confidentiality Notice
All rights reserved. These materials are confidential. This document is being
submitted with the explicit understanding that no part of these materials would
be reproduced or published in any form or through any means whether
electronic, mechanical, photocopying or with the aid of any information storage
or retrieval system, nor would the materials be disclosed to third parties without
the express and prior written authorization of eXel Solutions.
Procedure Preparation of Relations Diagram consists of the following steps – .............................................................................................................................................. 76
22.19. TREE DIAGRAM ............................................................................................ 77
• Conducting failure mode and effects analysis (FMEA);
• Performing Design of Experiments (DOE) to identify critical
variables; and
• Benchmarking to remove ambiguity.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 28/87
12. Statistical significance
Six sigma means six standard deviations. One standard deviation is a
value such that roughly two-thirds of all values in a set fall within the
range from one standard deviation below average to one standard
deviation above average. Sets of values which can be characterized by
the average and standard deviation may be modeled by the normal
distribution. For 6 sigma the total range spans 12 standard deviations. As
the sigma value increases, a larger area under the “bell curve” is
included: 50% at +- 0.67 sigma, 68.3% at +- 1 sigma, 99.7% at +-3
sigma, greater than 99.999999% at +- 6 sigma.
6σ concept assumes that a process can shift 1.5 standard deviations as a
regular matter. If the process shifts that much, they argue, the tails of
the process would lap over the tolerance limits if the process width were
kept at ±σ equating the tolerance of the process. To avoid that, they set a
target for a process where the limits are narrow enough so that a 1.σ shift
will not shift the edge of the process beyond the tolerance limit. To do
this, they equate the tolerance of the process to ±σ. The tail of the
process distribution is not supposed to be closer than 1σ to the edge of
Understanding Six Sigma March, 2010
Confidential | Six Sigma 29/87
the specification or tolerance limit. That means that the edge of the
process distribution should end at ±4σ from the center. The value of 4.5
comes from the value of 6 less the 1.σ shift.
Six Sigma at many organizations simply means a measure of quality that
strives for near perfection. But the statistical implications of a Six Sigma
program go well beyond the qualitative eradication of customer
perceptible defects. It’s a methodology that is well rooted in mathematics
and statistics.
The objective of Six Sigma Quality is to reduce process output variation
so that ±six standard deviations lie between the process specification
upper and lower limits. This will allow no more than 3.4 defect Parts per
Million (PPM) opportunities, also known as Defects Per Million
Opportunities (DPMO), to be produced.
As the process sigma value increases from zero to six, the variation of the
process around the mean value decreases. With a high enough value of
process sigma, the process approaches zero variation and is known as
“zero defects.”
Understanding Six Sigma March, 2010
Confidential | Six Sigma 30/87
Decrease your process variation (remember variance is the square of your
process standard deviation) in order to increase your your process sigma.
The end result is greater customer satisfaction and lower cost.
13. Concept of 1.5 sigma shift
Using the table we will find that 6 sigma actually translates to about 2
defects per billion opportunities, and 3.4 defects per million
opportunities, which we normally define as 6 sigma, really corresponds to
a sigma value of 4.5. Where does this 1.5 sigma difference come from?
Motorola has determined, through years of process and data collection,
that every process varies and drifts over time - what they call the Long-
Term Dynamic Mean Variation. This variation typically falls between 1.4
and 1.6.
After a process has been improved using the Six Sigma DMAIC
methodology, we calculate the process standard deviation and sigma
value. These are considered to be short-term values because the data
only contains common cause variation -- DMAIC projects and the
associated collection of process data occur over a period of months,
rather than years. Long-term data, on the other hand, contains common
cause variation and special (or assignable) cause variation. Because
short-term data does not contain this special cause variation, it will
typically be of a higher process capability than the long-term data. This
difference is the 1.5 sigma shift. Given adequate process data, you can
determine the factor most appropriate for your process.
The reporting convention of Six Sigma requires the process capability to
be reported in short-term sigma -- without the presence of special cause
variation. Long-term sigma is determined by subtracting 1.5 sigma from
our short-term sigma calculation to account for the process shift that is
known to occur over time.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 31/87
14. Quality significance of six sigma
Quality, defined traditionally as conformance to internal requirements,
has little to do with Six Sigma. Six Sigma is about helping the
organization make more money. To link this objective of Six Sigma with
quality requires a new definition of quality. For Six Sigma purposes
quality can be defined as the value added by a productive endeavor.
Quality comes in two flavours, potential quality and actual quality.
Potential quality is the known maximum possible value added per unit of
input. Actual quality is the current value added per unit of input. The
difference between potential and actual quality is waste. Six Sigma
focuses on improving quality (i.e., reduce waste) by helping organizations
produce products and services better, faster and cheaper. In more
traditional terms, Six Sigma focuses on defect prevention, cycle time
reduction, and cost savings. Unlike mindless cost-cutting programs which
reduce value and quality, Six Sigma identifies and eliminates costs which
provide no value to customers, waste costs
15. Key Concepts of Six Sigma
At its core, Six Sigma revolves around a few key concepts.
Critical to
Quality:
Attributes most important to the customer
Defect: Failing to deliver what the customer wants
Process
Capability:
What your process can deliver
Variation: What the customer sees and feels
Stable
Operations:
Ensuring consistent, predictable processes to
improve what the customer sees and feels.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 32/87
16. Six sigma methodology
16.1. DMAIC versus DMADV
What's the Difference Between Six Sigma DMAIC and DMADV?
We know that everything in business is a process, right? Sales people
have a list of companies and contacts that they work in a certain fashion
to produce a sale, production receives an order and schedules the
manufacturing, the product is built, packaged, shipped and invoiced.
When the packing department has a problem with their process, though,
should they fix it with a DMAIC or DMADV (also referred to as DFSS) type
project?
16.2. The Similarities of DMAIC and DMADV
Let's first look at the DMAIC and DMADV methodologies and talk about
how they're alike. DMAIC and DMADV are both:
• Six Sigma methodologies used to drive defects to less than 3.4 per
million opportunities.
• Data intensive solution approaches. Intuition has no place in Six
Sigma -- only cold, hard facts.
• Implemented by Green Belts, Black Belts and Master Black Belts.
• Ways to help meet the business/financial bottom-line numbers.
• Implemented with the support of a champion and process owner.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 33/87
16.3. The Differences of DMAIC and DMADV
DMAIC and DMADV sound very similar,. The acronyms even share the
first three letters. But that's about where the similarities stop.
DMAIC Define
Measure
Analyze
Improve
Control
• Define the project goals and customer
(internal and external) deliverables
• Measure the process to determine current
• Performance
• Analyze and determine the root cause(s) of
the defects
• Improve the process by eliminating defects
• Control future process performance
When To Use DMAIC
The DMAIC methodology, instead of the DMADV methodology, should be
used when a product or process is in existence at company but is not
meeting customer specification or is not performing adequately.
DMADV Define
Measure
Analyze
Design
Verify
• Define the project goals and customer
(internal and external) deliverables
• Measure and determine customer needs and
specifications
• Analyze the process options to meet the
customer needs
• Design (detailed) the process to meet the
customer needs
• Verify the design performance and ability to
meet customer needs
Understanding Six Sigma March, 2010
Confidential | Six Sigma 34/87
The DMADV methodology, instead of the DMAIC methodology, should be
used when:
• A product or process is not in existence at your company and one
needs to be developed
• The existing product or process exists and has been optimized
(using either DMAIC or not) and still doesn't meet the level of
customer specification or six sigma level
Occasionally a project is scoped as a DMAIC for incremented process
improvement when it really required a DMADV methodology
improvement. And it was a month into the project that one realized this!
Don't be discouraged about the work one put into the DMAIC because 1)
it's happened to more businesses than just yours, 2)you understand the
process at a much greater detail than you did initially, and 3) you were
able to practice not just DMAIC skills but also DMADV.
Pick yourself up, dust yourself off and re-craft your define piece of the
project so you can begin with a fresh look at the project and solutions.
You never know what insights you'll have now that you may not have
been aware of before.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 35/87
17. Six Sigma Organisation
Provide Vision, Lead
Review, Business decisions
Evoke behavioral change,
Provide required support
Train & Coach, Lead
Monitor, Drive improvement
17.1. Champions
Six Sigma champions are high-level individuals who understand Six
Sigma and are committed to its success. In larger organizations Six
Sigma will be lead by a full time, high-level champion, such as an
Executive Vice-President. In all organizations, champions also include
informal leaders who use Six Sigma in their day-to-day work and
communicate the Six Sigma message at every opportunity. Sponsors
are owners of processes and systems who help initiate and co-ordinate
Six Sigma improvement activities in their areas of responsibilities.
CHAMPIONS
FUNCTIONAL CHAMPION
MASTER BLACK BELT
BLACKBELTS
GREENBELTS
TEAM
•Helps Implementation
•Works with Black Belt on
project
•Indicate barriers to
function Leaders
Understanding Six Sigma March, 2010
Confidential | Six Sigma 36/87
17.2. Master Black Belt
This is the highest level of technical and organizational proficiency.
Master Black Belts provide technical leadership of the Six Sigma program.
Thus, they must know everything the Black Belts know, as well as
understand the mathematical theory on which the statistical methods are
based. Master Black Belts must be able to assist Black Belts in applying
the methods correctly in unusual situations.
17.3. Black Belt
Candidates for Black Belt status are technically oriented individuals held
in high regard by their peers. They should be actively involved in the
process of organizational change and development. Candidates may
come from a wide range of disciplines and need not be formally trained
statisticians or engineers. Black Belts receive 160 hours of classroom
instruction, plus one-on-one project coaching from Master Black Belts
or consultants.
17.4. Green Belt
Green Belts are Six Sigma project leaders capable of forming and
facilitating Six Sigma teams and managing Six Sigma projects from
concept to completion. Green Belt training consists of five days of
classroom training and is conducted in conjunction with Six Sigma
projects. Six Sigma Black Belts help Green Belts define their projects prior
to the training, attend training with their Green Belts, and assist them
with their projects after the training.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 37/87
18. Six Sigma Requirements
While many other requirements are applicable, we personally believe that
these are the most important:
• Management Team Buy-In and Support
• Education and Training
• Resource Commitment
• Link to Compensation
18.1. Management Team Buy-In and Support
If your executive team is not fully supportive and proactive in establishing
your Six Sigma Quality initiative, you will be wasting everyone's time. As
with any successful initiative implementation, everyone's actions need to
be tied to the initiative.
A useful exercise in determining buy-in is to list out all the individuals of
the management team on a piece of paper. Then assign a positive,
neutral or negative to each person signifying what you believe to be their
support for the initiative. Your job, before beginning the implementation,
is to move every single person to at least a neutral position, if not
positive. Education can help with this goal.
18.2. Education and Training
What training is necessary? Well, it depends on who is getting trained.
Here's a snapshot table identifying the major groups of individuals, the
suggested training agenda, approximate cost and duration of the training.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 38/87
18.3. Resource Commitment
As discussed above, Black Belts(BB) &/or Master Black Belt(MBBs) need
to be identified and trained. But more importantly, they need to be
assigned to your Six Sigma efforts almost 100%; 50% application yields
less than a 50% result. In addition to BBs and MBBs, you should be ready
to assign 5-15% of key employees' time to specific projects.
18.4. Link to Compensation
We all work and perform responsibilities for a paycheck, right? Just as you
expect your factory to produce Y widgets per hour and your bank to
process Z deposits per day, you should expect projects to be contributed
to and successfully completed in a prescribed time period. And employees
executing well should be compensated well. The quickest way to initiative
success is to tie results to the business bottom line, create performance
goals, and compensate employees appropriately.
19. Six Sigma Implementation
19.1. How to Select a Quality Improvement Project
The right project can have a tremendous effect on your business. If done
properly, processes will function more efficiently in 3 to 6 months,
employees will feel satisfied and appreciated for making business
improvements and ultimately shareholders will see the benefit.
19.2. Linking Quality to Finances
The Quality profession has always been about improving processes,
products and services. From TQM to PDCA to Six Sigma, all Quality
methodologies are focused on eliminating defects and the root causes of
those defects. It involves products that satisfy your customers, running
processes at greater efficiencies, producing less waste and increasing
Understanding Six Sigma March, 2010
Confidential | Six Sigma 39/87
business productivity. All of this, of course, is based on the fact that these
processes are driving financial benefits.
Now, we'll look at each of these areas with application to small
companies. After each major requirement will be a synopsis and
discussion around whether it is easier to implement Six Sigma Quality in a
small company or a large company.
20. Application of Six Sigma to Small Companies
20.1. Management Team Buy-In and Support Easier
Compared to large companies, small company management teams are
typically closer on a personal basis. Pulling the small company team
together for a short meeting can be done in minutes, as opposed to days
for a large company. Because smaller companies are more agile, it is
typically easier to achieve management team agreement that a standard
methodology can help achieve results. Although politics are always
present, less may be required in a smaller company to come to
agreement and buy-in for implementing Six Sigma Quality.
20.2. Education and Training Harder
Although the costs presented on page is somewhat standard, buying in
bulk always produces a discount. This is the main reason we believe
education and training is harder (costlier) for smaller companies. Time is
money -- time away from the office is lost revenue and production for
both small and large companies alike. But the return on investment is a
function of the potential savings of the business. For a behemoth like GE
or Motorola, standardized processes can yield enormous savings -- a large
potential exists prior to implementing Six Sigma. For smaller companies,
the savings potential may not be as great. The return on investment may
not be as quick or as significant. You know your business and processes
better than anyone else. How great are the potential savings?
Understanding Six Sigma March, 2010
Confidential | Six Sigma 40/87
20.3. Resource Commitment Slightly Harder
The key issue here is employee time. As mentioned above, time is money
for both employees that are partially assigned to teams and project
leaders. BUT -- we must remember to see the forest through the trees.
Any time dedicated to process improvement will be recouped in process
productivity going forward for all time. But it again boils down to the
potential savings that are available in your business.
20.4. Link to Compensation Easier
No brainer being able to link compensation to Six Sigma implementation
is much easier in a small company, compared to a larger company.
Decisions in general are quicker for small companies that are why they
are more agile. The key will be applying the rigor and written procedures
that larger companies do well. Formal performance appraisal systems
need to identify what is to be accomplished, what success looks and feels
like, and how an employee will be compensated. Just be sure to involve
your Human Resources representative to ensure that employee
responsibilities are being modified in the appropriate manner.
20.5. Selection of Project
The right project can have a tremendous effect on your business. If done
properly, processes will function more efficiently in 3 to 6 months,
employees will feel satisfied and appreciated for making business
improvements and ultimately shareholders will see the benefit. If done
improperly, a project may be selected that doesn't have the full business
buy-in, project roadblocks may not be removed due to other business
priorities, the team may feel ineffective and the end result may be less
than ideal. No one wins in this situation, especially the quality manager
who may look to these same people the next time a need arises. So how
do we make sure we select projects in-line with business priorities?
Understanding Six Sigma March, 2010
Confidential | Six Sigma 41/87
Here are five guidelines to keep handy the next time we are evaluating
potential quality improvement projects:
• Ask business leader for the three greatest issues facing the
business. Make sure project is one of the issues or is directly
related. This will ensure that your management team is giving the
project the proper attention and quickly removing roadblocks.
• What are the three greatest issues as seen from the eyes of your
customers? Look through customer complaint logs, listen to call
center telephone conversations and call customers that have
stopped your company service. Create a Pareto Chart to prioritize
issues.
• Is the project manageable? Can the project realistically be
completed by a team within six months? If longer, you may lose
members as they move to other jobs or the team may feel
frustrated that they're not making a difference.
• Will the team have a measurable impact on the business processes
or financial bottom line? Don't embark on a project without knowing
what the benefits are to the business. This will keep team motivated
along the way.
• What is process capability? If you haven't been measuring your
process, how do you know it needs improvement? Make sure you
know what amount of defects the process is currently producing and
define your project desired outcome.
Every business is different and you should ensure that your specific
priorities are taken into account when evaluating potential projects.
Spreadsheets or databases can help you organize potential projects by
assigning evaluation categories, values and weightings to create a
consistent selection process.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 42/87
20.6. Linking Quality to Finances
The Quality profession has always been about improving processes,
products and services. From TQM to PDCA to Six Sigma, all Quality
methodologies are focused on eliminating defects and the root causes of
those defects. It involves products that satisfy your customers, running
processes at greater efficiencies, producing less waste and increasing
business productivity. All of this, of course, is based on the fact that these
processes are driving financial benefits. If it didn't make sense financially,
would you still do it? In some cases you might, but as a rule of thumb you
can't sustain a business unless you bring in revenue and produce a profit.
The six sigma methodology, in particular, emphasizes the financial results
of a project. What does all of this do for your company?
1) Before a project is initiated, a scoping analysis of financial benefits
is performed. This allows management to Prioritize along with other
business specific factors, potential projects.
2) After or during the completion of a project, a final Financial Analysis
is performed based on the actual results of the project. This forces the
business to quantify the return on investment for the Quality
department. Is it paying off as you would expect any other investment
in the business?
3) It opens the eyes of management to what is actually happening on
the floor, in the shop and in the cubicles, translating day-to-day
activities into terms that they are concerned about - meeting the
budget, increasing profits and driving shareholder value.
4) It educates employees about the whole financial picture. Because
Six Sigma uses employees to drive projects and improvements, it also
modifies their work behaviors to cut costs and increase profits.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 43/87
Many businesses have found the successful recipe for Quality. When
employees are allowed to exit from the intellectual vacuum where they
are deprived of business and financial information, they then can see the
whole picture. They understand how their actions do make a difference
and how they are needed to make business processes successful. You
don't need "Six Sigma" necessarily, but you do need to tie process
improvements to financial results in order to be successful. There are six
fundamental steps that must be achieved before Six Sigma can become a
reality within any organization:
Step-1: Successful performance improvement must begin with senior
leadership. Start by providing senior leadership with training in the
principles and tools they need to prepare their organization for success.
Using their newly acquired knowledge, senior leaders direct the
development of a management infrastructure to support Six Sigma.
Step-2: Systems are developed for establishing close communication with
customers, employees, and suppliers. This includes developing rigorous
methods of obtaining and evaluating customer, employee and supplier
input.
Step-3: Training needs are rigorously assessed. Remedial basic skills
education Is provided to assure that adequate levels of literacy is
possessed by all employees.
Step-4: A framework for continuous process improvement is developed,
along with a system of indicators for monitoring progress and success. Six
Sigma metrics focus on the organization's strategic goals, drivers, and
key business processes.
Step-5: Business processes to be improved are chosen by management,
and by people with intimate process knowledge at all levels of the
organization. Six Sigma projects are conducted to improve business
performance linked to measurable financial results.
Step-6: Six Sigma projects are conducted by individual employees and
teams lead by Green Belts and assisted by Black Belts.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 44/87
Although the approach is simple, it is by no means easy. But the results
justify the effort expended. Research has shown that firms that
successfully implement Six Sigma perform better in virtually every
business category, including return on sales, return on investment,
employment growth, and share price increase.
21. CASE STUDY
21.1. Six Sigma Implementation in GE
GE launched a corporate wide quality improvement strategy in 1995 when
Jack Welch, chairman and CEO committed GE's empire to reach 6
quality by year 2000. Operating at about the industry average of 3 sigma
in 1995, Mr. Welch's vision is a stretch goal, but GE is making progress to
achieve 6 performance and estimates that 6 will contribute an extra
$5 billion to net earnings through the end of the century. In 1998 Mr.
Welch expects 6 to yield about $750 million in net benefits. Jack Welch,
Chief Executive Officer of GE, realized that attaining Six Sigma Quality will
require retraining their entire workforce to think and act like engineers -
an enormous feat with remarkable benefits.
When the program began ,GE selected 5 Criteria to measure
progress Towards an aggressive Six Sigma Goal
Sl No General Electric Balanced Score Card
1 Cost of Poor Quality Financial Customer Satisfaction Customer 2 Internal Performance Internal 3 Design for Manufacturing(DFM) Innovative & Learning
4 Supplier Quality
The above table compares the GE criteria with four traditional Balanced Score Criteria.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 45/87
21.2. Potential Benefits of 6 sigma program
• Six Sigma oriented organizations will spend 1% or less of each sales
dollar on cost of non-conformance while a 4 Sigma organization will
spend as much as 25%.
• $200 million in documented savings over the cost of training for
1997 at GE
• Expected annual revenue and cost savings of $10 - 15 billion at GE
when Six Sigma is fully realized.
• GE's 1997 operating margin, a critical measure of business
profitability and efficiency, surpassed 15% level for the first time.
• The entire GE workforce actively involved in quality initiatives and
total customer satisfaction
Five Critical to Quality (CTQ) Measures taken by GE
Six Sigma Quality at GE starts and ends with the goal of total customer
satisfaction. To understand the needs of the customers, GE stresses five
"CTQ’s" –
1) Get the customers what they want
2) When they want it
3) On time
4) Undamaged
5) Working.
21.3. Use of Scorecards
These five CTQ’s were identified in the early stages of GE's efforts and are
continually assessed through the use of "Scorecards". Scorecards allow
rapid focus on products and processes that do not meet customer's
desires and track implemented solutions until the discrepancy is erased.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 46/87
Once a project at GE is identified as meeting at least one of the CTQs, it is
then led through the Six Sigma process by a specially trained employee
known as a "Black Belt."
GE's Six Sigma Process: Define; Measure, Analyze; Improve;
Control
Using the techniques of Six Sigma, GE has identified and defined the phases used in optimising processes. These phases, known by the acronym DMAIC, are explicitly followed and with that, successful results
are noted. Each step in the cyclical DMAIC Process is required to ensure the best possible results. The DMAIC steps include the following:
Step 1: Define
• Define the Customer, their Critical to Quality (CTQ) issues, and the
Core Business Process involved.
• Define who customers are, what their requirements are for products
and services, and what their expectations are.
• Define project boundaries - the stop and start of the process.
• Define the process to be improved by mapping the process flow.
Step 2: Measure
• Measure the performance of the Core Business Process involved.
• Develop a data collection plan for the process.
• Collect data from many sources to determine types of defects and
metrics.
• Compare to customer survey results to determine shortfall.
Step 3: Analyze
• Analyze the data collected and process map to determine root
causes of defects and opportunities for improvement.
• Identify gaps between current performance and goal performance
• Prioritize opportunities to improve.
• Identify sources of variation.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 47/87
Step 4: Improve
• Improve the target process by designing creative solutions to fix
and prevent problems.
• Create innovative solutions using technology and discipline.
• Develop and deploy implementation plan
Step 5: Control
• Control the improvements to keep the process on the new course.
• Prevent reverting back to the "old way".
• Require the development, documentation and implementation of an
ongoing monitoring plan
• Institutionalize the improvements through the modification of
systems and structures (staffing, training, and incentives).
21.4. Statistical Tools
In order to optimize any and all processes within GE, a thorough and
rigorous analysis of the applicable data is processed using Minitab, an
extremely powerful statistical data analysis program. Minitab enables
analyses such as:-
1) Run and Pareto charts
2) Fishbone diagram
3) Control charts: X-Bar, R, S, X-bar-R, X-Bar-S, and Box-Cox
Transformation for non-normal data, gage linearity and accuracy.
Minitab provides the means to accomplish all of these as well as calculate
sigma - the bottom line number needed for achieving success.
Training: An Integral Part of GE's Six Sigma Program
In order to become a Six Sigma company, GE has undertaken extensive
training of all personnel and ensured strong and determined leadership.
Since the onset of this massive training effort, excellent results have been
achieved.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 48/87
The result of this training push is impressive as there are now nearly
4000 full-time quality 'Black Belts' (BB) and 'Master Black Belts'
(MBB). Additionally, there are more than 60,000 'Green Belt' (GB)
"part-time" project leaders who have completed at least one Six Sigma
project. All GB, BB and MBB projects must show a 90% reduction in dpm
to be called successful.
To become a GE certified Green Belt (GB), the following criteria must
be met.
• Complete 2 weeks of DMAIC training within a one year period
• Complete a total of two (2) Six Sigma Green Belt Projects within
each one year period.
To become a GE certified Black Belt (BB), the following criteria must
be met:
• Complete 2 full weeks of DMAIC training.
• Complete a total of eight (8) Six Sigma BB Projects in each one-
year period.
Black Belts are primarily focused on training/guiding/driving all Green
Belts under their jurisdiction to complete their 2 projects per year. Black
Belts will approve each phase of those projects while getting regional
manager concurrence on approving the "Define" & "Closure" phases of
each project. However, the individual Green Belt (and their respective
managers) will be held responsible for the completion of his/her own GB
Project; the purpose of the Black Belts is not to "complete" projects for
the GB, but rather to review, analyze, approve, and assist.
Master Black Belts must meet similar requirements to become certified as
do Black Belts, with the exception being MBB's must complete 4 weeks of
intense DMAIC training. As the BB is the mentor of the GB, the Master
Black Belt is the mentor, coordinator, and driver of GE's entire Six Sigma
program. Thus, they are vital to the success or failure of the program. A
Understanding Six Sigma March, 2010
Confidential | Six Sigma 49/87
"Champion" is usually the Business Manager for each particular
component. The champion is the one who sponsors the project as being
beneficial to his/her particular business unit and ultimately gives
approval. Champions may have many hundreds of projects under their
approval. And, before credit is given to management and quality workers,
a certified Black Belt must prove that the new process fixes the problem
permanently.
21.5. Leadership is Key
Since Jack Welch has tied promotions to quality improvement, employees
desiring to stay and prosper at GE have opened up to a complete change
in their way of thinking. Every employee is trained to think and act like an
engineer, i.e. analyze anything and everything; ensure everything
functions at an optimum level.
21.6. An Example of GE's Success with Six Sigma
One of GE Plastics' subsidiaries, Super abrasives, a leading manufacturer
of industrial diamonds, has fully embraced the Six Sigma program and its
successes clearly indicate the approach works. The following
improvements occurred at Super abrasives between Six Sigma's start in
1995 and the end of 1997:
• Operating margins rose from 9.8% to 25.5%
• Variable manufacturing costs fell 50%.
• The number of carats per manufacturing run rose 500%.
• On-time deliveries improved 85%.
• Product quality improved 87%.
• Late deliveries to customers declined 85%
• Billing mistakes fell by 87%
• Capital expenditures decreased by 40%
Understanding Six Sigma March, 2010
Confidential | Six Sigma 50/87
21.7. Conclusion
An enormous training effort is essential to a program such as GE's Six
Sigma Quality. It involves retraining an entire workforce to think and act
like engineers. GE has spent hundreds of millions of dollars since 1995 to
mold a workforce that lives customer satisfaction through continuous
quality improvement. The complexity of a Six Sigma Quality program
would be impossible to initiate and sustain without this type of dedicated
and thorough approach to training.
Such a training program is the result of nothing less than full dedication
from the entire leadership structure, starting at the top.
GE's increasing operating margins are the final proof that the combination
of inspired leadership and intensive training are the critical aspects of a
successful Six Sigma Quality program.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 51/87
22. Quality Improvement Tools (QC Tools)
22.1. Introduction to QC Tools
There are certain simple tools and techniques which can naturally be
positioned within the TQM philosophy. Many of these tools can easily be
utilized for everyday problem solving or for realizing opportunities, and
can thus be effectively used to support the implementation of the
methodology for quality management and improvement.
This section contains a list of such tools, which, although by no means
exhaustive, includes the most popular and commonly used techniques;
these are briefly described and arranged in such a way as to be easy to
access.
22.2. Tally sheet
Tally Sheets are forms for recording data in a simple manner. There are
three main types of tally sheets;
a) Recording Tally Sheets
b) Inspection Tally Sheets, and
c) Check Lists
Purpose
To devise a simple form to facilitate collection of data
Procedure
The steps involved in creating Tally Sheets are -
a) Describe clearly the purpose of collecting data.
b) Decide who will collect the data and when, where and how it will be
collected.
c) Determine how much data will be required.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 52/87
d) Decide the format for collecting and presenting data in suitable
classifications.
e) Prepare a draft form and check if it meets the purpose.
f) Finalise the form and give it a title.
g) Collect the data and present for further analysis.
Figure 1: Tally sheet
Problem Month
July August Septembe
r
Total
A III II IIII 09
B IIII III II 10
C IIII III IIII 12
D II III II 07
Total 14 11 13 38
Figure: 2: Tally sheet for Typing mistakes
Mistake Type July Total
Clerk 1 Clerk 2
Punctuation IIII III 07
Wrong Page
Numbers III IIII 07
Spelling IIII III 08
Missed
Paragraph III IIII 07
Centering IIII IIII 09
TOTAL 20 18 38
Understanding Six Sigma March, 2010
Confidential | Six Sigma 53/87
22.3. Graph
Graphs and Charts are pictorial presentations of data, making it easy to
spot trends, ratios, comparisons among different groups of data. The
more common types of graphs and charts are Line Graphs, Bar Charts,
and Pie Charts. In addition, there are a number of variants and
combinations of these.
Purpose
To present numerical data in an easy-to-spot visual form. Line graphs are
used to depict change or variation over time. Bar charts are used for
comparing quantities between persons, regions, time intervals etc. Pie
charts are used to show percentages or proportions of different
components of a specific item.
Procedure
The essential steps in the preparation of various types of graphs and
charts are -
1. Select the type of chart or graph most suitable for the type of data
to be depicted.
2. Decide the units and scales of items to be shown on X-axis and Y-
axis.
3. (In case of Pie chart scale is always the same - 100% = 3600)
4. Fill the information on the graph sheet.
5. Join required points to complete lines or bars.
6. Color or shade the lines or bars to distinguish between different
groups or classes. Provide a key to explain the meaning of the
colors and shadings.
7. Provide an appropriate title.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 54/87
Figure: 3: Line Graph
100 Name of student -------------- Roll No. -----------
Class: ---------
95
90
85 Average
Marks
Obt. 80
75
70
1 2 3 4 5
6
Subject : Maths Phy Chem. Eng. Drawing Mechanics
22.4. Bar Chart
A bar chart is a graphical representation of discrete groups or categories
of data, shown in such a way that clear comparisons can easily be made.
A bar chart is frequently used to emphasize a point; this will dictate the
way in which the chart is drawn. The chart is normally used to emphasize
the variation and unevenness in data. Using this information, further
investigation could follow to determine why the variation was occurring.
The items are usually ranked from high to low, with the lengths of the
bars indicating the value or frequency that a bar represents.
A special version of the bar chart is the 100% bar chart which has all its
bars of equal lengths; each bar (representing 1000% of the item) is
Understanding Six Sigma March, 2010
Confidential | Six Sigma 55/87
subdivided according to the size of its components.
When the data are spread across a continuous range of values, a bar
chart is equivalent to a histogram.
AVERAGE TEMPERATURE DURING WINTER IN MUMBAI
1998 1999 2000
33
31`
29
27
25
October November December January
Figure : 4 : Bar Chart
22.5. Block Diagram
If every activity that is part of a process is represented by a block (box),
and all blocks are connected by lines representing the interfaces between
activities. A macro level view of the process is obtained; this is called a
block diagram. The diagram traces the paths that any information,
necessary actions or materials can take between the original input and
the final output of the process. For each activity in the process, there is a
determination of the output it produces, what other activities it feeds into,
and, through the identification for particular work activities, there is also a
determination of who performs the activity.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 56/87
Fig. 5: Block Diagram: Problem Solving Process
22.6. Histogram
Histograms or Frequency Distribution Diagrams are bar charts showing
the distribution pattern of observations grouped in convenient class
intervals and arranged in order of magnitude.
Purpose
To study the pattern of distribution of observations and draw
conclusions based on the distribution.
Procedure
The steps in preparing histograms are
1. Collect data (a minimum of 50 observations) on a specific item.
2. Arrange all values in an ascending order.
3. Divide the entire range of values into convenient number (usually
≤ the square root of the number of observations) of groups each
representing an equal class interval.
4. Note the frequency of observations in each group.
5. Draw X-axis and Y-axis and decide the scales for class on X-axis
and number of readings or frequency on the Y-axis.
SELECTION DEFINITION ANALYSIS SOLUTIONS
PRESENTATION EVALUATIOTRIAL RUN
ACTION PLAN
FOLLOW-UP PREVENTIVE
ACTION REVIEW
Understanding Six Sigma March, 2010
Confidential | Six Sigma 57/87
6. Plot the points and draw bars.
7. Give the histogram a suitable title.
8. Study the pattern of distribution and draw conclusions regarding
normality of distribution and process capability.
22.7. STRATIFICATION
Stratification is a technique to present data into different groups or
categories to bring out the differences between groups and explain the
‘abnormality’ of histograms. The classification may be based on machines,
operators, shifts or any other source of variation.
Purpose
To ascertain the difference between different categories and to analyse
the reasons behind abnormal distribution or too wide dispersion shown by
the histogram of the total data.
Procedure
The steps for stratifying data starts with an ‘abnormal’ histogram of
composite data. The further steps are -
1. Examine the data for sources of variations.
2. Classify the composite data into different groups.
3. Prepare histograms of the reclassified data.
4. Examine the histograms of each group of data for ‘normality’.
5. Give the new histogram an appropriate title.
22.8. SCATTER DIAGRAM
Scatter Diagram is a special type of graph in which two characteristics
whose relation is to be studied are taken on the X and Y axes. A dot at an
appropriate point is placed on the graph for each observation. The pattern
made by the scatter of the dots can indicate if there is a relation between
the two and if so whether it is direct or inverse and whether it is strong or
mild.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 58/87
Purpose
To test hbypothetical relationship between two sets of variables or
characteristics.
Procedure
The steps in the preparation of a scatter diagram are -
1. Tabulate available data.
2. Select the characteristics or variables to study the relationship.
3. Use X-axis for one and Y-axis for the other variable.
4. Decide appropriate scales.
5. For each observation involving the relation between the two
variables place a dot on the graph sheet.
6. Observe the pattern of distribution of the dots and infer as follows
a. If the dots are distributed randomly, there is no apparent
relationship.
b. If the dots are distributed closely around a sloping line, there is
a strong relationship.
c. If the dots are scattered loosely around such a line, there is
likelihood of a mild relationship.
d. If the slope of the line is from SW to NE, there is a direct and if
the slope is from SE to NW, there is an inverse relationship.
22.9. CONTROL CHART
Control Charts are graphical presentations showing if a process is under
control. Control charts are of two main types -
1. Control Chart for Variables or measurables, and
2. Control Chart for Attributes.
Control chart for attributes has a few categories like portion or percent
defective (p), number of defectives (pn), number of defects per unit (u)
and number of defects per subgroup (c).
Control charts are tools to monitor processes.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 59/87
Purpose
The purpose of all control charts is to track a process with a view to take
timely corrective action as soon as the process goes out of control.
The steps involved in setting up control chart for variables - X & R charts
are
1. Determine the size of sample group.
2. Design a suitable Tally sheet.
3. Collect data under standard operating conditions (without
adjustments)
4. Calculate the average (X) and range (R, the difference between the
largest and the smallest value in the group).
5. Calculate the average of averages – X.
6. Calculate the average range - R.
7. Calculate the control limits for X chart using the formula
UCL = X + A2* × R
LCL = X – A2* × R
* Values of A2 for more common group sizes are given in table 1.
8. Calculate the control limits for the R chart using
UCL = D*4 × R
LCL = D*3 × R
* Values of D3 & D4 for common sample group sizes are given in the Table
1 for other group sizes refer to any standard book on SQC or SPC.
9. Divide the graph into two portions for (1) X Chart and (2) R Chart.
10. Periodic observations are taken on X-axis and X & R on Y-
axis.
11. Select appropriate scales and draw central lines and control
limits.
12. Plot the observations and look out for indications of the
process going out of control or other trends.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 60/87
VALUES OF A2, D3 AND D4
Group Size A2 D3 D4
4 0.729 0 2.282
5 0.577 0 2.115
6 0.483 0 2.004
8 0.373 0.136 1.864
10 0.308 0.223 1.777
Table 1: Constants to calculate control limits
22.10. CONTROL CONTROL CHART – TALLY EXAMPLE
Commuting Times (min.) – A. M.
STEP 1 :
STEP 2 :
Xavg = 74.6
Ravg = 36.0
n = 5
STEP 3 :
UCL8 = Xavg + A2 Ravg
= 74.6 + (58) (36.0)
= 74.6 + 20.88
= 95.48
1
2
3
4
5
Week
6
7
8
9
10
55 90 100 70 55 75 120 65 70 100
75 95 75 110 65 85 110 65 85 80
65 60 75 65 95 65 65 90 60 65
80 60 65 60 70 65 85 90 65 60
80 55 65 60 70 65 70 60 75 80
X =
71
72 76 73 71 71 90 74 71 77
R=25 40 35 50 40 20 55 30 25 40
Understanding Six Sigma March, 2010
Confidential | Six Sigma 61/87
LCL8 = Xavg - A2 Ravg
= 74.6 – 20.88
= 53.72
UCLR = D4 Ravg
= (2.11) (36.0)
= 75.96
LCLR = D3 Ravg
= 0
STEP 4:
X Chart
100
95
90
85
80
Xavg = 85.48
75
70
65
60
55 LCL = 53.72
50
1 2 3 4 5 6 7 8 9 10
Fig 6: X CHART
Understanding Six Sigma March, 2010
Confidential | Six Sigma 62/87
80 R Chart
UCL = 75.86
75
70
65
60
55
50
45
40
Ravg = 36.0
35
30
25
20
15
10
5
LCL = 0
0
1 2 3 4 5 6 7 8 9
Fig 7. R CHART
Understanding Six Sigma March, 2010
Confidential | Six Sigma 63/87
22.11. CONTROL CHART FOR ATTRIBUTES
The steps for selling up a control chart for attributes are -
1. Decide the defect to be tracked.
2. Determine the type of chart (p, pn, u or c) that is applicable.
3. Design a suitable tally sheet and collect data.
4. Calculate the average and control limits.
5. Prepare a graph sheet with successive observations on X-axis and the
defect level on Y-axis. Select appropriate scales.
6. Draw the lines for average and control limits.
7. Plot the observations and join the points to get a line graph.
8. Look for signs of process going out of control or other trends to take
timely action.
Some occurrences that can give indications of the process going out of
control or show trends are:
1. A single observation out of control limits.
2. A series of seven consecutive observations on the same side of the
average.
3. A series of seven consecutive readings showing an increasing or
decreasing trend.
4. A cyclic, periodic or recurring wavy pattern. Cause must be
investigated.
5. Consecutive very high and very low readings may indicate
unnecessary adjustments
Understanding Six Sigma March, 2010
Confidential | Six Sigma 64/87
22.12. PROCESS CAPABILITY
The data collected for control charts can also be used to ascertain process
capability. One way to check if the process is capable or not is to draw
lines for specification limits on the control chart. If the difference between
UCL and LCL is less than specification tolerance, the process is capable of
meeting the specification; otherwise it is not capable. From the data one
can also directly assess process capability without drawing control charts.
The steps involved in this are:
1. Calculate standard deviation (σ) by using the applicable formula
In case of X and R chart (for variables) R
σ = ------ (value of d2 for different group sizes is given
below) d2
Group size 4 5 6 8 10
d2 2.06 2.33 2.53 2.85 3.85
In case of a p chart (for fraction defective)
p × (1 - p)
σ = √ n
2. Draw a histogram to ensure that the process is under control. If the
distribution is not normal, find the causes and eliminate them to get
normal histograms, before applying tests to check process capability.
3. Calculate Process capability index Cp using formula
Specification Tolerance
Cp =
Process Tolerance (= 6σ)
If the value of Cp is greater than or equals 1, the process is capable; if it
is less than 1, the process is not capable.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 65/87
4. Evaluate the centering of the process by calculating index Cpk using
the formula.
Upper Spec. limit – X
C pk = ––––––––––––––––––––––– or 3σ
X – Lower Spec. Limit, = ————————— whichever is lower
3σ
5. If Cpk is greater than or equals 1, the process is meeting specification
requirements.
If Cp ≥ 1, but Cpk < 1, the process is capable, but is not meeting the
requirements because of poor centering.
22.13. PARETO DIAGRAM
Pareto Diagrams are a special type of histograms. The bars in Pareto
Diagrams are rearranged in descending order of their heights, showing
individual contribution of each factor as well as cumulative contributions.
Purpose
To identify high priority items by separating the ‘vital few’ from the ‘trivial
many’ or as they are now known ‘useful many’.
Procedure
Preparation of a Pareto Diagram has the following steps:
1. Design a suitable Tally Sheet to collect data. :
2. Collect required data.
3. Calculate the contribution of each item.
4. Arrange the items in descending order of their contributions. If there
are too many small items, combine them under ‘others’.
5. Draw X and Y axes. Different items (in descending order) are on X-
axis and the frequency of their occurrence on Y-axis. An additional Y-
axis is drawn on the right to indicate percentages. Select appropriate
scales.
6. Draw bars representing the frequency of the items.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 66/87
7. Draw bars from the second item onwards at a level where the bar of
the previous item ends. This is an optional step not always
recommended, but it makes the next step easier.
8. Draw a line graph connecting the diagonals of the new bars drawn as
instructed in step 7.
9. Title the diagram suitably.
Fig 8: Pareto Diagram Problem:
In a film distribution company, customer complaints last year as follows;
Key Descendin
g
Cumulativ
e
A Broken Shipping
case
------------
5
D 40 40
B Damaged Film ------------
15
C 25 65
C Poor Print ------------
25
B 15 80
D Wrong Print ------------
40
F 08 88
E Subject in film not
treated well
------------
03
A 05 93
F Late Shipment -----------
08
G 04 97
G No Leaders Guide -----------
04
E 03 100
Total -----------
100
Make a pareto diagram for this company and select the most important problem
to solve.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 67/87
100 100%
90
80
70
60 Most Important
Problem to solve
50 wrong print
40
30
20
10
D C B F A G E
22.14. Brainstorming
Brainstorming is a technique to generate a large number of ideas from
members of a group in a structured manner. Brainstorming is an activity
which promotes group participation and teamwork, encourages creative
thinking and stimulates the generation of as many ideas as possible in a
short period of lime.
The participants in a brainstorming meeting are invited on the basis of
their particular knowledge and experience, and are expected to contribute
to the topic under discussion. An atmosphere is created where everybody
Understanding Six Sigma March, 2010
Confidential | Six Sigma 68/87
feels free to express themselves. The production of random ‘off the top of
the head’ ideas is encouraged; the emphasis is on quantity rather than
quality. No criticism, expression of doubt or hasty judgment of the ideas
is allowed until after the brainstorming session; this is crucial if the
barriers to creative thinking (such as the fear of seeming foolish or
impractical) are to be overcome.
All ideas, without exception, are recorded and made visible to all the
participants. Each input and contribution is recognized as important, and
the output of the whole session is seen in context. The continuing
involvement of each participant is assured and the group's future is
reinforced by mapping out the exact follow up actions (analysis and
evaluation of the ideas) and the future progress of the project.
Purpose
To generate a large number of ideas or options or alternatives. As we
shall see in some of the tools to follow, the ideas may be for identifying a
problem or finding causes for the selected problem, or devising solutions,
or identifying areas of resistance to the implementation of the proposed
solution.
Procedure
The steps involved in Brainstorming are -
1. The group elects a facilitator.
2. Facilitator writes the topic and a short purpose of Brainstorming on
a flip chart.
3. He asks the members by turn to suggest one idea at a time. He
notes it down on the flip chart briefly.
4. After every member has had his first turn, he starts another cycle.
5. A member who has no fresh idea to offer may pass.
Ideas are not to be evaluated at this time, however, clarification
may be sought if the idea is not clear.
6. A member can build on an idea suggested by another member.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 69/87
7. The process is continued till all members pass.
It is essential to remember some Do’s and Don’ts for idea-generation part
of the process of Brainstorming.
Do’s Don’ts
a. Encourage everyone to a. Lei some persons dominate
participate, others.
b. Stress quantity rather b. Criticise or ridicule an
than quality of ideas, idea however wild or silly.
c. Encourage humour, c. Permit interruptions.
d. Keep all ideas posted in a d. Tape record proceedings. manner all members can see. e. Restrict ideas.
Once the session on idea generation is complete, the group can take up
prioritising and selecting ideas for immediate follow-up. The steps
involved in this part of Brainstorming are -
1. Check if apparently identical ideas are really same or there is some
different angle.
2. Identify and group together related ideas.
3. Have a brief discussion in support of ideas (surely not against any
ideas) if desired.
4. Shortlist ideas for follow-up action by consensus or voting.
5. If voting is used every member gets the same number of votes, say
five or 10. One can give all votes to one idea or distribute his votes
one each to as many ideas or any other combination. The total votes
polled by each idea are counted and a priority list finalised.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 70/87
22.15. CAUSE AND EFFECT DIAGRAM
Cause-and-Effect Diagrams, also known as Fishbone Diagrams because of
their shape or Ishikawa Diagrams after their founder Dr. Kaoru Ishikawa,
depict the relation between an ‘Effect’ and various possible ‘Causes’ for
the effect.
Purpose
To generate in a structured manner, maximum number of ideas regarding
possible causes for a problem by using brainstorming technique.
Procedure
Generation of a Cause-and-Effect diagram consists of the following steps -
1. Agree on the effect or problem for which causes are to be searched.
Display the 'Effect' and draw the backbone or spine.
2. Determine the main categories of causes.
3. Enter them in rectangles and connect them to the spine by the ‘middle
bones’.
4. Brainstorm to collect as many ‘causes’ in each category as possible
and enter them as sub-categories.
5. Discuss the relative importance of the causes.
6. Shortlist a few causes, by consensus or voting as the important
causes and circle them.
7. Test to verify the finding.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 71/87
Figure 9: Cause & Effect Diagram
Employers Materials
How to Achieve
Company
Objective
Train & Develop All employees to their
full potential
Develop an effective company Business
Systems
Build Database of market &
customer Requirements
Ownership & Involvement
Suggestion Schemes
Reward & Recognition
Motivate & empower all Safety & Standardization Concern
Communication
Variety Reduction
Vendor Development
Value Engineering
Optimize Materials
Training Needs Identification
Product training
Skill Building
Succession Planning
Training & Development
Information Flows
Accurate & timely information
User friendly
Simplified Systems
Integrated business systems
Customer feedback
Price
Benchmark
After sales service
Improve customer Contact
Understanding Six Sigma March, 2010
Confidential | Six Sigma 72/87
22.16. FLOW CHART
Flow Charts are diagrams documenting the steps in a process using
standard symbols.
Purpose
To document clearly the flow of a process as a series of operational
steps as carried out at a given time. The Flow Charts are then used to
identify duplication of efforts or missing steps with a view to make the
process more efficient.
Procedure
The steps involved in the preparation of a flow chart of a process are -
1. Gather, from all related individuals, information on each step in
the process as it exists at the time.
2. If information from different sources is not tallying, check back to
find the exact situation.
3. Prepare a flow chart showing starting position and end of the
process, various steps, decision points and movement from step
to step. Use the following standard symbols.
Ellipses to show the start and finish of the process
Rectangles for individual steps in the process
Diamonds for decision points
Line with arrowheads indicates movement from step to
step with direction
4. Discuss with all concerned individuals to confirm that the
document actually depicts what happens. Make corrections if
necessary.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 73/87
5. Study the chart for identifying any duplication, missing steps or
loopbacks.
6. Brainstorm to find ways of eliminating the deficiencies listed in
step 5.
7. Prepare a revised chart incorporating the suggestions for
improving the efficiency of the process. Get it approved.
8. Follow-up on the implementation to ensure accrual of gains.
22.17. ARROW DIAGRAM
Arrow Diagrams are flow charts of processes or projects showing all
necessary steps in appropriate order along with the time required for
each step, the earliest the step can be completed and the latest time
by which it must be completed. This tool is used as CPM (Critical Mean
Path) as well as in PERT (Programme Evaluation and Review
Technique).
Purpose
To plan and schedule projects or processes, monitor their progress.
Procedure
The steps in the preparation of an Arrow Diagram are
1. Identify all the steps or activities in the process or project.
2. Determine the order of activities and alternate routes.
3. Prepare a flow chart of the process or project.
4. Check the time required to perform each step or activity.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 74/87
5. Determine the time for reaching various steps in the process.
Where a process converges after an earlier bifurcation, indicate
the higher of the converging routes’ timings.
6. For every step calculate the earliest possible time of completion
as well as the latest time by which the step must be completed to
complete the process on schedule.
7. On the route on which there is a ‘slack’, check if there is a
technical reason to favor early or late completion of the activity.
Indicate this as a note to the diagram.
Understanding Six Sigma March, 2010
Confidential | Six Sigma 75/87
Electrification
Procure Electric
Material
Estimates Procure building Foundation Superstructure
Roofing Plaster
Drawing & Design Work
Doors &
Windows
Painting & Finishing
Acquire Land
Fig. 11: Arrow Diagram ; Construction of a House
1
3 4 5
6 9
7 8 1
10
2
Material
Six Sigma March 10, 2010
Confidential | Six Sigma 76 /87
22.18. RELATIONS DIAGRAM
Relations Diagrams are cause and effect diagrams used in complex
situations, particularly when a number of causes are interrelated.
Purpose
To generate a diagram showing the relations between cause and effect as
well the interrelations between various causes.
Procedure
Preparation of Relations Diagram consists of the following steps –
1. Decide the problem or the ‘effect’ for which causes are to be found. Write
it in the big rectangle in the centre of the board or flip chart paper.
2. Brainstorm to generate primary causes and write them in different
rectangles around the central rectangle with effect. Connect each of the
causes to the effect with lines with arrows pointing towards the effect. It
would be convenient if causes likely to be related are written adjacent to
one another.
3. Keep asking 'why?' to generate secondary and tertiary causes for each of
the primary causes. Keep asking 'Why' till a root cause is reached. Follow
the same procedure for all the primary causes.
4. Connect secondary, tertiary and root causes to the effect through a
series of lines with the arrows always pointing towards the effect.
5. If the primary causes are also related as cause and effect, connect them.
Connect the other related causes to show as many interrelations as
possible.
6. Identify the root causes to which the effect is connected by a large
number of routes. Such root causes are likely to be the causes
contributing maximum to the effect.
Six Sigma March, 2010
Confidential | Six Sigma 77 / 87
7. Reach a consensus on the main contributory causes for follow-up action.
If need be voting can be used as described under brainstorming.
8. Give the diagram a suitable title.
22.19. TREE DIAGRAM
Tree Diagrams are visual presentations of means of achieving goals in a
cascading sequence of goals-means-goals-means. These are arranged as a
tree with branches and sub-branches.
Purpose
To develop alternative means for solving a problem.
Procedure
The steps in the preparation of a Tree Diagram are –
1. Define the problem and the primary goal or objective. Keep it wide
enough so that no possible solution is excluded.
2. Brainstorm to find the means to achieve the primary goal.
3. The means identified in step 2 become the secondary goals. Brainstorm
again to find the means to achieve the secondary goals.
4. Continue the process by asking the key question 'How?' every time.
5. When one reaches the end of the line going down to some basic means,
brainstorming is done again to identify a few of the alternative means
which are most likely to contribute to the solution of the defined
problem.
6. Title the diagram suitably.
Note:
A set of cards for the primary and secondary goals may be used to facilitate
collection or ideas before drawing the diagram.
Six Sigma March, 2010
Confidential | Six Sigma 78 / 87
Fig.12: Tree Diagram
22.20. AFFINITY DIAGRAM
This is an organizing tool, useful, for example, in sorting out ideas generated
through a brainstorming session. It is particularly necessary when a large
amount of information, ideas, opinions or issues have been collected in
situations when a process needs defining, or customer requirements need
identifying, or when a problem needs solving.
The technique organizes the collected pieces of information into groupings
based on the natural relationships that exist among them. The number of
groupings is limited to a maximum of 10. A single piece of information can
constitute an independent group in its own right. A heading is created for
each group, capturing its meaning.
Reward & Ascertain Recognition
Identify work
Capability
Develop a list
Motivation
Education
Good Faculty
Skill Developments
Empowerment
Better Facilities
Involvement
Transport
Housing
Training
needs
Training
Six Sigma March, 2010
Confidential | Six Sigma 79 / 87
The technique is useful in reducing an otherwise unmanageable amount of
information into a smaller number of homogeneous groups which are much
easier to handle independently, prioritize in order of significance or allocate
to specific projects for further study or investigation.
Affinity Diagrams are visual presentations of ideas arranged in groups of
related ones from among a very large number of ideas.
Purpose
To group ideas generated by brainstorming into groups of closely related
ones. The tool is particularly useful for deciding characteristics and features
of new products being developed.
Procedure
Preparation of Affinity Diagram consists of the following steps
1. Decide the topic.
2. Collect ideas by brainstorming.
3. Rearrange the ideas into groups of related ideas. Use a card for
each group.
4. Arrange the groups according to the relationship among the
groups.
5. Present the arrangement in the form of an Affinity Diagram.
6. Title the diagram suitably.
Six Sigma March, 2010
Confidential | Six Sigma 80 / 87
Fig. 13: An Affinity diagram of House
22.21. COST-BENEFIT ANALYSIS
This is a technique for assessing the viability of an action in monetary terms.
The costs of taking a particular action are compared to the benefits
achievable from the future outcome. It can also be used to compare, in
money terms, a number of problem solutions or plans of action
Technical Details
• Floor Plan
BUILD UP AREA
• No. Of Rooms
• Details of Material
used
Location
• Central Gardens
• Near to school &
Offices
• Good Transport,
Telegraph, Postal,
educational facilities
Nearby
Amenities
• Water Park
• Cafeteria
• Club
• Library
Features
• Air conditioned
• Mosaic designer tiles
• Kitchen Garden Lift
• High quality fittings
Economy
• Reasonable Pavia
• Easy installment
• Loan facility
Six Sigma March, 2010
Confidential | Six Sigma 81 / 87
A necessary first step should be to decide on the period over which the cost-
benefit analysis will be performed. All the potential costs in setting up the
action or solution should be considered at this stage. The next step is to
consider all the factors involved which will either incur costs or provide
benefits. Consideration should be given to hidden cost factors such as
training, maintenance costs and so on. Costs and benefits should be
estimated conservatively.
The final analysis should be based on the calculation of the benefit to cost
ratio, and the net benefit, perhaps in conjunction with non-financial aspects.
The results can be used to evaluate a number of options.
22.22. CUSTOMER - SUPPLIER RELATIONSHIP CHECKLIST
This type of checklist can be used to help in the assessment of the
relationship between the supplier and the (external or internal) customer. It
can help in the identification of customer requirements, in the better
definition of the process, and in the unbiased assessment of the process
performance and of customer satisfaction or dissatisfaction. The checklist
should attempt to answer the following questions, which can be allocated to
three main groups:
Group 1. Questions about issues concerning relationships with the
customer:
1.1. What are your primary inputs - in terms of product or service?
1.2. Who are your customers - internal and external recipients of your
output?
1.3. What are your customer's requirements? What are the methods you
use to determine these requirements?
Six Sigma March, 2010
Confidential | Six Sigma 82 / 87
1.4. How satisfied are your customers with your product or service? How do
you measure their satisfaction?
Group 2. Questions about issues concerning the process performance:
2.1 What are the characteristics of your process output that can be
measured to determine whether it meets your customer's
requirements?
2.2 What major quality problems prevent you from meeting your
customer's requirements?
2.3 What are the obstacles standing in the way of resolving these quality
problems, and what would it take to remove these obstacles?
Group 3. Questions about issues concerning the relationship with the
supplier:
3.1 Which suppliers or subcontractors affect your capability to meet your
customer’s requirements? How do you select them?
3.2 What are your primary supplies and what are your requirements for
these supplies?
3.3 How do you communicate your requirements to your suppliers and
subcontractors? Do you help them to meet these requirements?
3.4 How satisfied are you with your suppliers or subcontractors? Do you
provide feedback to them about their performance?
Six Sigma March, 2010
Confidential | Six Sigma 83 / 87
22.23. SELECTION OF RIGHT COMBINATION
In the preceding pages, we have seen numerous tools for achieving,
maintaining and improving quality. In theory, all the 17 tools stand on their
own and can be used alone. However, in practice, in work life situations, one
may need to use a combination of several of them in a series, one after the
other. To point this out we have sometimes used data collected for one tool
while illustrating the use of another tool. (E.g. in examples of Histogram and
Pareto Chart, we used data collected in the examples of Tally Sheets).
Most statistical tools start with collection of data, for which an appropriate
Tally Sheet has to be designed as the first step. In most judgmental tools,
generating a large number of ideas or alternatives is very important. The
technique of Brainstorming will be used for idea generation. This too has
been usually mentioned among the steps in the procedure for the tool.
Besides this, for solving a problem, a series of tools may have to be used.
For instance, one may use a Cause-and-Effect Diagram to find the causes for
a problem, collect data (Tally Sheet), study the relative contributions of
various causes and prioritise (Pareto Diagram), analyse the data (using
Scatter Diagram of Stratification) and after solving the problem, may
monitor the process by using an appropriate Control Chart.
If the problem is more complex, one may use a Relations Diagram to study
the causes of the problem and then use a Tree Diagram to search for
solutions. For developing a new product, one may use an Affinity Diagram to
group customer requirements in convenient categories and then use a Matrix
Diagram or Matrix Data Analysis Diagram to assist in designing the new
product to meet those requirements.
Six Sigma March, 2010
Confidential | Six Sigma 84 / 87
The tools based on the use of statistics can be employed by an expert
working alone, but the judgmental tools can be used to advantage only by
teams of trained practitioners of the tools. These tools will require
interaction between different functions within the company and teamwork
between members of groups making use of the tools. The importance of
teamwork and active participation of various functions cannot be
overemphasized.
Experience and practice of tools will be the best guides in the selection of the
right tool or combination of tools for a given purpose. As mentioned in the
introduction, the tools are easy to understand but difficult to master. Only
practice will make you perfect. So, make frequent use of the tools and
techniques and develop expertise in their use.
Six Sigma March, 2010
Confidential | Six Sigma 85 / 87
Table 2: SPC TOOLS – SELECTION (SUMMERY)
TOOL OBJECTIVES METHODOLOGY WHEN TO USE
TYPICAL USER
1. PDCA
(Plan, Do, Check, Act )
Problem solved
by trial & error
Plan the work; execute it;
take action if there is deviation between desired & actual results. Repeat the cycle time till deviation is
reduced to zero.
When
powerful tools unknown.
Mostly line
workers.
2. Data
collection & Analysis
− Assess Quality
Control − Control a product
− Regulate a process
− Accept / Reject a
product − Interpret observations
Define specific reason for
collecting data. Decide on mes. criteria Attribute vs. Variable vs. Rank; assure
accuracy of measuring equipment ( min. 5 times greater than produced requirement ) ; randomise,
stratify data collection ( time , material, machine, operator, type & location of
defects ) analyse data using several S.P.C. D.O.E. tools.
At all times Universal.
3. Graph charts
− Display trends
− Condense data
− Explain to other
Select two or more parameters to be displayed; determine method of display (bar, line of circle or graphs
are the most common); Select the most appropriate scale of the parameter for maximum visual impact.
At all times Universal.
4. Check sheets
* Tally
Sheets
− Transform raw data
into categories
Group cells in
semipictorial fashion
Determine categories into which data into which
subdivided ( e.g. types of defects, location of defects, days in the week, etc. ).
Enter quantities in each category. * For tally sheets divide
variable being recorded into 10 levels or cell. Plot cell boundaries or mid points.
Make tally ( with slash marks) of the number of observation in each cell.
In preparation for a
Histogram or Frequency Distribution
Curve.
Universal.
Six Sigma March, 2010
Confidential | Six Sigma 86 / 87
5. Histogram
Frequency Distribution
Translate data into a picture of
the average & spread of a quality
characteristics
Convert tally sheet data into bar graph (Histogram) or
line graphs (Frequency Distribution) showing the relationship between various
values of a quality characteristics & the number of observations (or percentage of the total) in
each value.
For process capability
studies in pre production or production
Universal tool for
prioritization in mfg. Or white collar
work.
6. Brain
storming
* Generate as
many ideas to solve a problem of improve a process utilizing
synergistic power of a group.
from the trivial many. Concentrate attention on the
former
* Gather a group most
concerned with problem; define problem precisely ask each member to write down the cause of problem or
improvement ideas; then, open the floor for an outpouring of ideas, rational
or irrational; no criticism allowed. Record ideas; narrow down the most worthwhile ideas.
* Initial
problem solving “ Process” Improvement
Quality
Circles Improvement teams
7. Cause &
effect (Ishikawa Fish bone
Diagram)
* Organise
problem causes into main groups &
subgroups in order to have total visibility of all causes &
determine where to start corrective action
* Define the problem;
constructed a “Fishbone” diagram with the major causes (e.g. material,
machine, method & man) as the main “branches” & add detail causes within each main causes as “twigs”.
Quantify the speed limits established for cause & its effect upon the problem. If relationship between the
cause & effect can be shown quantitatively draw a box around the cause. If the
relationship is difficult to quantify underline the cause. If there is no proofs that a cause is related to the
effect, do not mark the cause with a circle. Experiments with these in
PDCA fashion until root cause is located.
Problem
Analysis
Universal
Six Sigma March, 2010
Confidential | Six Sigma 87 / 87
8. Control Charts
Maintain the parameter with
minimum variation after major cause
causes have been captured & reduced.
Select the control parameter product characteristics study
process capability. Set control limits – Monitoring process