Charting
Charting is the most effective way to display relative differences be- tween data points, particularly as they relate to sequential changes. SA offers basic chart generating capabilities and export options for more advanced charting applications.
Q-Das export is also available for more advanced analysis and processing capabilities. Q-DAS export has been implemented for appropriate relationships, GD&T checks, dimensions, and vector groups.
Available Charts
Vector Group Charting
The following chart types are available for vector groups:
-
Moving Range SPC Chart. Moving Range charts are used to monitor individual values over time with respect to control limits for the individual values.
-
Bullseye Chart. Bullseye Charts are used to pot two parameters relative to a specific goal.
-
Run Chart. A Run Chart or run-sequence plot is a graph that displays observed data in a time sequence, providing a basic plot of a Primary and Auxiliary parameter.
Feature SPC Charting
Moving Range SPC Charts can be added for the following features:
-
Relationship Criteria. Charting is available for Average, Max, Min, RMS and StdDev values.
-
Geometry Relationship (GR) Feature Criteria. The options will depend on the geometry type and reflect the available criteria.
-
GD&T Feature Check Results. Charts can be used to plotted changes in features checks results when multiple checks are made based upon a single annotation.
-
Dimension Magnitudes. Charts can be used to plotted changes in dimension values
Chart Controls
Chart Plot Region Controls:
The following basic chart configurations can be made:
-
Titles. Chart titles can be edited as needed.
-
Rainbow Coloring. A red and green colorization can be ap- plied to the chart back ground with respect to the control lim- its.
-
Control Limits. A dotted line can be drawn on the chart to dis- play the upper and lower control limits. This can be turned on and of and the Ordinate value adjusted (see Ordinate below).
-
Specification Limits. The chart plotted area can be adjusted to display Observation values within the specified High and Low limits.
-
Chart Range. The plotted value index can be adjusted to dis- play data within a specific range of values. Both a start and stop control index can be specified.
Chart Buttons
-
Print. The Print button will export the current chart to you de- fault printer.
-
JPG. The JPG button will export the current chart as an image file saved in the selected directory.
-
Copy. The Copy button will save an image of the current chart to the windows clipboard and can then be pasted in another document.
Right-Click Export to Excel
The right-click menu for a chart offers an Export to Excel option which will export a *.csv file containing the raw observation data used for the chart.
Chart Statistical Results
Ordinate
The Ordinate is a term which defines the y-coordinate or vertical of a point in a two-dimensional system. In SA charts this value is used to drive the placement of the upper and lower control limits and defines represents the Sigma value or standard deviation used.
Upper and Lower Control Limits (UCL & LCL)
These are the lines drawn above and below the process control line (PLC average or RBAR running average) in Range and Observation charts. They are computed from the available data and placed equidistant from the PCL line. It is formulated using the average deviation times the positive and negative standard deviation, which in this case is the Ordinate. Points plotted above or below the control limits are considered out of control.
Process Sigma
Process Sigma is a measure of the variation in a process relative to customer requirements. We measure defects on a scale of defects per million opportunities (DPMO). Any instance of failing to meet customer requirements is a defect, so a high number for DPMO is unde- sirable. This is implemented
Process sigma, as implemented within the context of SPC, is developed from the moving R average value -- it is NOT directly calculated from the data. The moving R values are the absolute value of the delta between adjacent observations. The average of these R values is R_ BAR. Estimated process standard deviation = R_BAR / 1.128.
Upper and Lower Specification Limits (USL & LSL)
A value that represents the highest and lowest range in a variable typically these limits are set by a customer requirement.
Cp and Cpk
-
Cp – Process capability. A simple and straightforward indica- tor of process capability
-
Cpk – Process capability index. Adjustment of Cp for the effect of non-centered distribution. (measures how close you are to your target and how consistent you are to your average performance.
Use an analogy of hitting a target to help understand. If you hit the target in the same spot forming a good group this is a high Cp (PRE- CISION). Now imagine that this tight grouping had actually landed on the bullseye, you now have a high Cpk (ACCURACY).
Kurtosis
Kurtosis is a measure of the sharpness of the peak of a frequency- distribution curve. It is a descriptor of the shape of a probability dis- tribution, which is used along with skewness. Kurtosis is sometimes confused with a measure of the peakedness of a distribution. How- ever, kurtosis is a measure that describes the shape of a distribution’s tails in relation to its overall shape.
Kurtosis quantifies whether the shape of the data distribution match- es the Gaussian distribution. Gaussian distribution has a kurtosis of 0. A flatter distribution has a negative kurtosis. A distribution more peaked than a gaussian distribution has a positive kurtosis.
Skewness
Skewness is a term in statistics used to describe asymmetry from the normal distribution in a set of statistical data. Skewness can come in the form of negative skewness or positive skewness, depending on whether data points are skewed to the left and negative, or to the right and positive of the data average.
When data is skewed to the right, the mean and the median of the set are both greater than the mode. (Mean is the average, Median is the data center, and Mode is the number which occurs the most). Further, the mean is greater than the median in most cases. Conversely, when data is skewed to the left, the mean and the median are both less than the mode. In addition, as a rule, the mean is less than the median.