B
BoothMan
We have two different instruments to measure the downdraft velocity in automotive spray booths. Our customer decided to perform an R&R study on the two measurement instruments to determine their capability. They selected 12 different locations in the booth and had two operators take two measurements at each location with each piece of equipment. The operators moved around the booth performing their measurements at different locations, i.e. operator 1 may have been at location 1 while operator 2 may have been measuring at location 7.
Our concern is that this study does not seem to be correct. The downdraft at any point in the spray booth is continuously fluctuating. You can measure 85 fpm and then seconds later a second measurement may read 101 fpm at the same location, for example. If you take a sufficient number of measurements around the booth, the average of a one set of readings will be close to the average of another set of readings but the readings at each location can vary significantly between any two sets of measurements.
We believe that the test as conducted isn't reading the same "part" as the measurements were made at different times and the actual downdrafts are varying continuously and is therefore different for each measurement. We think that unless a study with a very large number of measurements at each location was conducted the results will be meaningless. Can an expert on R&R studies comment? Thanks.
Our concern is that this study does not seem to be correct. The downdraft at any point in the spray booth is continuously fluctuating. You can measure 85 fpm and then seconds later a second measurement may read 101 fpm at the same location, for example. If you take a sufficient number of measurements around the booth, the average of a one set of readings will be close to the average of another set of readings but the readings at each location can vary significantly between any two sets of measurements.
We believe that the test as conducted isn't reading the same "part" as the measurements were made at different times and the actual downdrafts are varying continuously and is therefore different for each measurement. We think that unless a study with a very large number of measurements at each location was conducted the results will be meaningless. Can an expert on R&R studies comment? Thanks.