Taguchi Method
   Presented by:
   Bobby Wyrwa




   Dr. Genichi Taguchi   IE672-852
                         Professor Bernier
                         4/25/12
Electrical Communication
              Laboratories




Murry Hill, New Jersey                              Tokyo, Japan



        Dr. Taguchi – Head of R&D Productivity and Product Quality
Concepts
Quality should be designed into the product and
not inspected into it

Quality is best achieved by minimizing the
deviation from the target

The cost of quality should be measured as a
function of deviation from the standard and the
losses should be measured system-wide
Quality Designed Into the Product


Quality improvement begins at the design
stage
Continues through to the production stage
Inspection, screening, or salvaging does
not improve poor quality
Quality should be based on the philosophy
of prevention.
Minimizing Deviation From the
            Target
Quality is directly related to the deviation of a
design parameter from the target value
Properties skewed toward one end of an
acceptance range yet show a shorter life
expectancy

– Step 1: Specify a target value
– Step 2: Develop manufacturing process to meet target
  value
Quality As a Function of Deviation


Measuring deviations from a given design
parameter in terms of the overall life cycle
costs of the product

Scrap, rework, inspections, returns, or
product replacement
Limitations of Quality Control

The need for timing with respect to
product/process development

Techniques MUST be applied in the early
stages of the design

Taguchi method may not always apply
Design Parameters for Reduced
          Variation

Reducing the variation around the target
– Easier to attain quality
Highly used for industrial settings
Low cost solutions can be found by
adjusting the levels and controlling the
variation of OTHER factors
Cost savings exceed the cost of additional
experiments
Example
   Process objective: Economic
manufacturing of high quality (color,
size, …) tiles

   Problem: Uneven size due to
temperature variation in kiln

   Traditional approach: Redesign kiln for
more even temperature distribution
($.5M investment with no guarantee)

   Robust design approach: Find a set
product or process design parameters
that makes the size insensitive to
temperature variation

  Solution: Increase lime content from
1% to 5% in clay
Thank You



Questions and Comments via Moodle

Taguchi presentation

  • 1.
    Taguchi Method Presented by: Bobby Wyrwa Dr. Genichi Taguchi IE672-852 Professor Bernier 4/25/12
  • 2.
    Electrical Communication Laboratories Murry Hill, New Jersey Tokyo, Japan Dr. Taguchi – Head of R&D Productivity and Product Quality
  • 3.
    Concepts Quality should bedesigned into the product and not inspected into it Quality is best achieved by minimizing the deviation from the target The cost of quality should be measured as a function of deviation from the standard and the losses should be measured system-wide
  • 4.
    Quality Designed Intothe Product Quality improvement begins at the design stage Continues through to the production stage Inspection, screening, or salvaging does not improve poor quality Quality should be based on the philosophy of prevention.
  • 5.
    Minimizing Deviation Fromthe Target Quality is directly related to the deviation of a design parameter from the target value Properties skewed toward one end of an acceptance range yet show a shorter life expectancy – Step 1: Specify a target value – Step 2: Develop manufacturing process to meet target value
  • 6.
    Quality As aFunction of Deviation Measuring deviations from a given design parameter in terms of the overall life cycle costs of the product Scrap, rework, inspections, returns, or product replacement
  • 7.
    Limitations of QualityControl The need for timing with respect to product/process development Techniques MUST be applied in the early stages of the design Taguchi method may not always apply
  • 8.
    Design Parameters forReduced Variation Reducing the variation around the target – Easier to attain quality Highly used for industrial settings Low cost solutions can be found by adjusting the levels and controlling the variation of OTHER factors Cost savings exceed the cost of additional experiments
  • 9.
    Example Process objective: Economic manufacturing of high quality (color, size, …) tiles Problem: Uneven size due to temperature variation in kiln Traditional approach: Redesign kiln for more even temperature distribution ($.5M investment with no guarantee) Robust design approach: Find a set product or process design parameters that makes the size insensitive to temperature variation Solution: Increase lime content from 1% to 5% in clay
  • 10.
    Thank You Questions andComments via Moodle