120 likes | 146 Vues
Why/When is Taguchi Method Appropriate?. A new tip Every Friday. Friday, 3rd August 2001. New Tip #16. Taguchi Method 1 st Priority : V a r i a n c e R e d u c t i o n 2 nd Priority : Factor Effects (next 4 slides). Friday, 3 rd August 2001.
E N D
Why/When is Taguchi Method Appropriate? A new tip Every Friday Friday, 3rd August 2001
New Tip #16 Taguchi Method 1st Priority : Variance Reduction2nd Priority : Factor Effects(next 4 slides) Friday, 3rd August 2001
Symbols : Taguchi Method 1st Priority :VarianceReduction2nd Priority : Factor Effects • VarianceReduction : USE Factor-Effect Plot for S/N Ratio : Select ‘dominant’ Control Factor (and their Levels) such that “variance” is minimized Neutral Factor S / N RATIO A1 A2 A3 B1 B2 B3 C1 C2 C3 D1 D2 D3 • “put” the “mean-on-target” : USE Factor-Effect Plot for Mean : • Select one of the ‘neutral’ Control Factors as the “adjustment factor” Mean Adjustment Factor A1 A2 A3 B1 B2 B3 C1 C2 C3 D1 D2 D3
useful Mean Square = ----------------- = ----------------- Harmful Variance Symbols : Taguchi Method 1st Priority :VarianceReduction • S/N Ratio (Objective Function) Taguchi methods are experimental statistical methods to optimize a given process technology with respect to an objective function defined as • The Ideal Value of the S/N Ratio is (infinity). • Since the ideal value of the Ratio is (infinity), • the primary importance is shifted to “reduction in Variance” to 0 (zero) • making “improving mean” asecondary objective • (which is primary in conventional approach)
Symbols : Taguchi Method 1st Priority :VarianceReduction and “put” the “mean-on-target” • Variance is, in fact, reduced in presence of NoIsE and thus the product/process becomes “ROBUST” • Identify an “adjustment factor” that has little or no effect on the variance but has a large effect on the mean use the ‘adjustment factor’ to “put” the “mean-on-target”
Symbols : Taguchi Method 1st Priority :VarianceReduction2nd Priority : Factor Effects • Factor-Effect Plot for S/N Ratio : Select ‘dominant’ Control Factor (and their Levels) such that “variance” is minimized Neutral Factor S / N RATIO A1 A2 A3 B1 B2 B3 C1 C2 C3 D1 D2 D3 • Factor-Effect Plot for Mean : A, C, D Levels are selected from S/N ratio plot • Select one of the ‘neutral’ Control Factors as the “adjustment factor” • use this ‘adjustment factor’ to “put” the “mean-on-target” Do not select from this plot Mean Adjustment Factor A1 A2 A3 B1 B2 B3 C1 C2 C3 D1 D2 D3
Taguchi Method “inner” L9 array with “outer” L4 and L9 NoIsE arrays Taguchi Method “inner” L18 array with “outer” L4 and L9 NoIsE arrays Taguchi Method Why/When is TaguchiMethod not Appropriate? Friday, 27th July 2001 Friday, 20th July 2001 Friday, 13th July 2001 Earlier Tips Links below Tips 12, 11, 10
Taguchi Method “inner” L8 array with “outer” L4 and L9 NoIsE arrays Taguchi Method Useful at ALL Life-stages of a Process or Product Taguchi Method Performs Process “centering” or “fine tuning” Friday, 6th July 2001 Friday, 29th June 2001 Friday, 22nd June 2001 Earlier Tips Links below Tips 9, 8, 7
Taguchi Method Identifies the “right”NoIsEfactor(s) for Tolerance Design Taguchi Method Finds best settings to optimizeTWO quality characteristics Simultaneously 7. Taguchi Method When to select a ‘Larger’ OA to perform “Factorial Experiments” Friday, 15th June 2001 Friday, 8th June 2001 Friday, 1st June 2001 Earlier Tips Links below Tips 6, 5, 4
Taguchi MethodUsing Orthogonal Arrays for Generating Balanced Combinations of NoIsE Factors Taguchi MethodSignal-to-Noise Ratio for Quality Characteristicsapproaching IDEAL value 4. Taguchi Methodimproves " quality “ at all the life stages atthe design stage itself Friday, 25th May 2001 Friday, 18th May 2001 Friday, 11th May 2001 Earlier Tips Links below Tips 3, 2, 1
3. Taguchi MethodAppropriate forConcurrent Engineering 2. Taguchi Methodcan studyInteraction between Noise Factors and Control Factors 1. Taguchi’sSignal-to-Noise Ratiosare inLog form Friday, 4th May 2001 Friday, 27th April 2001 Friday, 6th April 2001 Earlier Tips Links below