Agenda 13:00-13:30 Registration 13:30-14:20 MSA-MINITAB 14:20-14:30 Break 14:30-15:20 SPC-MINITAB 15:20-15:30 Break 15:30-16:20 Case study (Healthcare & Banking) 16:20-16:30 Q&A July 14, 2006 in Taipei
MSA-MINITAB
Application in (Measurement Systems Analysis, MSA)
Measuring System.
What is a Measuring System? •The measuring device (Repeatability) •The person who is taking the measurement (Reproducibility)
3
Measurement Process
The ideal measurement system produce “true” measurements every time Quality of the measurement system is characterized by statistical properties Properties
Must be in Statistical Control Variability must be small compared to product specifications Variability must be small compared process variation
4
Basic Model σ 2 Total
=σ
2 Product
+σ
2 Measurement System
The Total Variation is equal to the real product variation plus the variation due to the measurement system
5
Minitab Exercise Capability and Measurement Error
Assume we have a process that has an actual sigma of 5 units and a mean of 70 units Also assume we have a measurement system that has the same measurement error as the process - sigma of 5 units Let’s use Minitab to simulate the effect of measurement error on process capability
6
Exercise - Continued
Follow these methods to create data to fit our process model: Creates a random normal distribution
7
Exercise - Continued
What value should we use for the mean of the measurement error?
Calculate observed process behavior.
8
Results of Simulations
15
LSL
USL
Frequency
Actual process variation No measurement error
10
5
0 30
15
40
50
60
70
80
90
100
110
Process
LSL
Frequency
USL
Observed process variation With measurement error
10
5
0 30 40 50 60 70 80 90 100 110
Observed
9
Effects of Measurement Error
Averages Averages Accuracy Accuracy
μ