by clicking the arrows at the side of the page, or by using the toolbar.
by clicking anywhere on the page.
by dragging the page around when zoomed in.
by clicking anywhere on the page when zoomed in.
web sites or send emails by clicking on hyperlinks.
Email this page to a friend
Search this issue
Index - jump to page or section
Archive - view past issues
FLEXO Magazine : October 2013
AnALYZing resuLts In order to understand how to analyze the results of a Gauge R&R, it is helpful to look at a few examples. In the first example, represented by Figure 2, the Gauge R&R was de- signed with a small range of parts and a specific goal: “Can the gauge adequately read highlight dots?” Figure 2 shows four components of variation, which are listed across the x-axis: • Gauge R&R, which is the sum of the next two components on the chart • Repeat • Reprod • Part-to-part The orange bars display the percentage of variance and the green bars display the percentage of total standard deviation. We will focus on the latter, since we only need to examine one or the other. We want the part-to-part percent- age study variation to be significantly higher than the Gauge R&R. This means the variation in the measurements was due primarily to the part-to-part differences—this is what we want to measure—rather than variation due to the repeatability or reproducibility of the gauge (instrument). The general guide- line is that Gauge R&R percent study of 10 percent or less is good; 30 percent or less is acceptable. In the example in Figure 2, the parts included were high- light dots on plates that covered a range from about 2 percent to 5 percent. The graph shows that the part-to-part percent study is significantly greater than the Gauge R&R. Figure 3 shows the numbers that go along with the chart in Figure 2. The numbers in the right column are the standard deviations in the left column expressed as a percent of the total variation at the bottom. In this example, we see the %SV for Total Gauge R&R is 14 percent, which is acceptable. Another key value is the “number of distinct categories.” The rule for this value is that if it is less than two, the measure- ment system cannot discriminate between parts, but if it is higher than five, the measurement system is acceptable and can discriminate between parts. A typical number would be somewhere between 5 and 12. The number of distinct catego- ries for this example is nine. The standard deviation of the total Gauge R&R is 0.10. This means that when measuring in this narrow range of highlight dots, we can expect the measurement to be between +/-0.30 (three standard deviations) of its nominal value 99.7 percent 22 FLeXo OCTOBER 2013 www.flexography.org IntroducIng duPontTM cyrel ® Performance Plates For superior flexo solid ink density, outstanding tonal range and low dot gain. Highest quality at high speed. see for yourself. For a free package sample and product ebrochure, visit www.cyrel.com/na. Copyright©2013DuPont.Allrightsreserved.TheDuPontOvalLogo,DuPontTMandCyrel®aretrademarksorregisteredtrademarksofE.I.duPontdeNemoursandCompanyoritsaffiliates. Figure 4