Statistical process control is the practice of sampling a process on a schedule, plotting the results on control charts and reacting only when the data show a signal. Its core idea is the split between common cause variation, which is left alone, and special cause variation, which gets investigated and removed. In a fab, thousands of SPC charts run automatically on film thickness, critical dimension, particle counts and tool sensors, each tied to an out-of-control action plan.
Put the new CMP removal-rate monitor into SPC with the same run rules as tool 3, and link it to the OCAP before Monday.
SPC tells you the process changed, not whether the product is good. Capability and spec limits answer that second question.
Also heard as
- statistical process control
Related terms
Control chart
Time-ordered plot of a process statistic with a centerline and limits that flag when the process has changed.
Common cause
Background variation built into a stable process from many small sources, present all the time.
Special cause
Specific, identifiable source of variation that is not part of the process's normal behavior and shows up as a chart signal.
OCAP
Out-of-control action plan: the scripted checklist that tells operators exactly what to do when an SPC chart fires.
Western Electric rules
Standard set of run rules that flag nonrandom patterns on a control chart, not just single points past the limits.