Re: Frequency of Gage R & R's
I agree with both Tom and PurduePete.
You have to think of all the components of the "Measurement System" and the impact that any change in them may have on the performance of the measurement system for a particular measurement. Some of the factors may be: change in operators, level of training they receive, change in the characteristic(s) & tolerances being measured, criticality of characteristic, change in measurment method, procedure, fixtures used, environmental conditons, repairs to gages, degradation over time, etc. When any of these occur/change, you must characterize the measurement system by doing a GRR study. Calibrations and R&R studies are the two methods that tell you how sensitive the measurement system is to change and the frequency of that change.
In addition, GRR study must be performed for all new measuring systems / gaging being introduced.
Also think about the purpose of measurement - inspection, process monitoring, process improvement, .... and the confidence you want in the measurements obtained. Much would depend on the process capability and the variation observed in the process. If your measurement results are going to be compared with some other measurement system (let's say your customer's), you had better done some GRR studies. If you are starting any process imrovement initiative (DOE/ Six Sigma) then MSA is a must. R&R studies can also point out possible areas of improvement.
Another important aspect is the customer's requirements - How often do they want you to perform GRR studies. I know of a OEM customer that used to insist on an R&R study report with every shipment !!
Don't forget that R&R is a short-term evaluation. According to Larry Barrentine (Concepts for R&R Studies- ASQ Press), "R&R is intended to be an ongoing periodic assessment or monitoring tool. It's not a 'do it once and we're done' issue." I don't think there is a thumb rule for deciding the frequency/periodicity of GRR studies for different types of equipment.
The MSA manual classifies R&R as 'Phase 2' study, which is "performed periodically for ongoing monitoring of the key sources of variation for continued confidence in the measurement system (and data being generated) and/or a signal that the measurement system has degraded over time.... How often should Phase 2 testing be performed? This decision may be based on the statistical properties of the individual measurement system and the consequence to the facility, and the facility's customers of a manufacturing process that, in effect, is not monitored due to measurement system not performing prpoperly.".
So when you decide to do GRR on a yearly or half-yearly basis, just make sure the above issues are taken into consideration, for every measurement system that you do R&R on. The cost & time needed to conduct GRR study is also a factor.
To complicate matters further, MSA has a few other studies apart from GRR - e.g bias, which can sometimes be a more serious matter because it can be a constant factor.
PurduePete said:
IMO, I do believe you will have a stronger position in making this decision if you have done them at least twice or maybe three times as objective evidence that your decision is valid, in other words, the Gage R&R did not change.
Absolutely!...and Welcome to the Cove, PP.
