【正文】 cess Cause Problem Control Identifying and Fixing Root Causes Will Help us Obtain the Desired Output f (X) Y = Process Capability 6? Overview Sustained Capability of the Process (long term) USL T Time 1 Time 2 Time 3 Time 4 Inherent Capability of the Process (short term) LSL Target Over Time, a “Typical” Process Will Shift and Drift by Approximately ??6? Overview “ Short Term Centered” versus “Long Term Shifted” Six Sigma Centered LSL USL T Process Capability SHORT TERM .001 ppm .001 ppm +6? LONG TERM LSL USL T ppm Six Sigma Shifted ? Process Capability Higher Defect Yield in Long Term Process Capability than Short Term Process Capability 6? ?? ??6? Overview Tying it All Together shift C D A B 1 2 3 4 5 6 C O N T R O L POOR GOOD TECHNOLOGY POOR GOOD A B C D Good Control/ Poor Technology Poor Control/Poor Technology Poor Control/ Good Technology WORLD CLASS!!! ??short term ??Problem Could be Control, Technology or Both 6? Overview Short Term Capability Short Term Capability Ratio (Cp) Cp = [ ] LSL 6??USL ] Example USL LSL ??= = ??6??[ ?? ( ????Cp = Cp = 1 LSL USL ?? ?? ??Process Mean 181。 Z T Target 0 A 3? Process The Definitions of Yield Final Test Process (Process 4) Pass Process 3 Process 1 Process 2 100 (Units Tested) 65 70 82 91 Yield 1 Yield 2 Yield 3 Loss 1 Loss 3 Rejects Loss 2 9 9 12 5 ? First Time Yield (Yft) = Units Passed Units Tested = 65 70 = ? Rolled Thruput Yield (Yrt) = (Yield 1) (Yield 2) (Yield 3) . . . . = 91 82 65 70 ( ( ( ( ) ) ) ) = 100 91 70 82 ? Normalized Yield (Ynm) = = 1/n (Yrt) () 1/4 = ( n: Total Number of Processes ) 6? Overview Yield Exclusive of Rework Probability of Zero Defects Average Yield of All Processes 6? Overview The Impact of Complexity Rolled Yield Number of Operations .4 .1 1 10 100 1,000 10,000 1,000,000 Process Mean Centered on Each Operation 1 10 100 1,000 10,000 1,000,000 Rolled Yield Number of Operations .5 As the Number of Operations Increases, a High Rolled Yield Requires a High ??for Each Operation 5?? 4?? 3?? 6?? 6?? 5?? 4?? 3??Process Mean Shifted ??at Each Operation 6? Overview Baselining Benchmarking an Existing Process p (x) Defects Benchmark Baseline Entitlement ? Benchmark.....A WorldClass Performance ? Entitlement.....Achievable Performance Given the Investments Already Made ? Baseline.....The Current Level of Performance Baselining = Current Process / Benchmarking = Ultimate Goal Some Basic 6?Related Tools 6? Overview Scatter Diagram Over Slept Car Would Not Start Weather Family Problems Other Pareto Diagram Frequency of Occurence Reasons for Being Late for Work Arrival Time at Work Time Alarm Went Off Materials People The Histogram Control Charts 6? Overview Some Basic 6?Related Tools The Fishbone Diagram Measurements Methods Technology Statement Cause Effect Being Late for Work Plot of Daily Arrival Time 9:15 7:00 7:15 7:30 7:45 8:00 8:15 8:30 8:45 9:00 Average Value Number of People Arriving at CRD Time 6? Overview LCL UCL Range Chart R Out of Control Condition LCL X UCL X Bar Chart Some Basic 6?Related Tools LCL = Lower Control Limit UCL = Upper Control Limit X = Mean R = Average Range Monitors Changes in Average or Variation Over Time Design of Experiments 6? Overview SCREENING OPTIMIZATION CHARACTERIZATION ? For Experiments Involving a Large Number of Factors ? Useful in Isolating the “Vital Few “ from the “Trivial Many” ? For Experiments Involving a Relatively Small Number of Factors ? Useful When Studying Relatively Unplicated Effects Interactions ? For Experiments Involving Only 2 or 3 Factors ? Useful When Studying Highly Complicated Effects Relationships DOE is More Effective Than Testing One Factor at a Time 6? Overview Using the “One Factor at a Time” Approach Reduce Commute to Work to 15 Minutes (without working an abnormal work schedule) The Goal The Variables Time of Departure from Home Route Taken to Work The Approach Try 3 Potential Routes at Current Departure Time (7:45), Select the Best Vary the Departure Time ?til we get to 15 Minutes Time of Departure 3 2 1 7:15 7:30 7:45 8:00 8:15 Route Combination Selected The Result Use Route 2 and Leave at 7:15 to Reach Goal 6? Overview Using “Design of Experiments” (DOE) Time of Departure DOE (i) Better Accounts for Interactive V