Paste your readings and see in seconds whether the process is stable and capable, and why.
SPC Engine answers the two questions every process review starts with: is the process stable (in statistical control), and is it capable of meeting the specification? Paste your readings and the tool picks the right control chart for your subgroup size, checks it for special causes, and gives Cp, Cpk, Pp and Ppk with the expected parts per million outside the limits, plus a sentence that says whether to reduce variation or re-centre.
Use it for measurements such as length, weight, torque or pressure (I-MR, X̄-R and X̄-S charts), and for counts of defective parts or defects (p, np, c and u charts).
Control limits, tests for special causes and capability indices follow the AIAG SPC manual and Montgomery. The results are tested against reference data sets analysed in specialised statistical software, and normality is checked before capability is reported. Read stability first: capability numbers from an unstable process do not predict the next batch.
The data behind “Try an example”: 15 individual readings with a specification of 23.0 to 25.0.
| Result | Value |
|---|---|
| Chart | I-MR |
| Centre line and limits | 24.167 · UCL 25.098 · LCL 23.236 |
| Tests for special causes | No signals: stable |
| Cp · Cpk | 1.07 · 0.90 |
| Pp · Ppk | 1.29 · 1.08 |
| Expected outside the limits | about 3,704 PPM |
The process is stable but not capable against the common 1.33 target. The spread alone uses 93% of the tolerance, so the main job is to reduce variation; the mean also sits a little above the middle of the tolerance.