Delta CS24D - Manual (Page 24)

24
8.3 Optimizing using the Analyze screen
The Analyze screen shows the predicted performance for the Teach data, which is shown as the number
of standard deviations separating each Sort Output. Values less than 3 indicate that the sensor has a
hard time differentiating between the target colors, and values greater than 5 indicate a high degree of
confidence.
(The range of the numbers
is from 0.0 to 100.0)
The pull-down box allows
you to quickly compare
the performance in Color
Only versus Color plus
Intensity modes. And by
selecting Custom from
the pull-down box, you
can manually adjust the
weighting factors and see
the affect on performance.
This unique capability
allows the RGB and
Intensity weightings to be
optimized to the actual
Teach data.
CAUTION: In order for the standard deviation prediction to be correct, it is essential that the
Teaching be done optimally. All eight Teach readings must be taken, the eight readings must include
representative samples of the range of colors that are considered permissible for that Sort Output,
and the sample objects must be at the exact distance from and orientation to the sensor as they will
be in actual operation. If the distance and/or orientation can vary, then the eight samples should
include this variation.
The key to optimizing performance of the CS24D lies in setting Weighting Factors (WFs) to achieve
the best differentiation for a given set of target colors (from previous Teach operations).
As explained above, The Intensity WF determines whether the sensor is in Color Only Mode (Intensity
WF = 0) or Color Plus Intensity mode (Intensity WF greater than zero).
However, the Weighting Factors are much more powerful than that. They are used to determine how
much the sensor relies on the various color values (blue, red, green, and intensity) to sort a given set of
target colors. Often, performance can be enhanced by over-weighting certain values, like blue and red,
and under-weighting other colors, like green and intensity.
The CS24D uses four Weighting Factors, one for the Intensity, and one each for the Red/Intensity,
Green/Intensity and Blue/Intensity ratios. The operation of the WFs is simple. If all four of the WFs =
1, then all four factors are weighted equally.
When adjusting WFs, the sum should always equally 4. For example, if the Intensity WF is set to zero
(Color Only mode), then other three WFs should be increased to keep the sum of the WFs at four.
To use optimized Weighting Factors, press the Save to Sensor icon. To view the Weighting Factors
currently stored in the sensor, press the Read from Sensor button. Changes to Sorting parameters do
not change Teach data, and changing parameters does not require retraining.