Paste your process data and instantly see UCL, CL, and LCL — with a live control chart that flags out-of-control points and Western Electric rule violations.
Paste numeric values separated by commas, spaces, or new lines. Minimum 5 data points required.
Choose your chart type, paste your data, and press Calculate to see control limits and a live chart.
Watch: Statistical Process Control: Know When to Act
15 days of order processing times logged. Enter the lab and build an XmR control chart to find where the process is in control — and where it is not.
Use the calculator above to paste your process data and instantly see Upper Control Limit, Centre Line and Lower Control Limit on a live control chart, with out-of-control points and Western Electric rule violations flagged. Control limits are the foundation of Statistical Process Control — the discipline that tells you when to act on a process and, more importantly, when not to.
Control limits are statistically calculated boundaries on a control chart — usually three standard deviations either side of the process mean. Points inside the limits represent common-cause (normal) variation; points outside the limits or violating Western Electric rules signal special-cause variation that needs investigation.
For an X-bar chart: UCL = x̄ + 3σ ÷ √n, LCL = x̄ − 3σ ÷ √n. Different chart types (X-bar R, Individuals, p-chart, c-chart) use slightly different formulas, but the principle is the same — limits that capture about 99.7% of natural variation, so points outside are statistically rare under normal operation.
A bottling line has a mean fill weight of 500g with a within-sub-group σ of 2g and sub-group size of 5. UCL = 500 + 3 × (2 ÷ √5) ≈ 502.7g; LCL ≈ 497.3g. Anything outside that range is a one-in-370 event under normal operation — almost certainly a real change.
When the chart shows seven consecutive points above the centre line (a Western Electric run rule), the calculator flags a likely process shift even though no single point breached the limits. That early warning is the whole point of SPC — catch shifts before they become defects.
Control limits separate normal variation from genuine process changes. They prevent operators tampering with stable processes (which makes things worse) and force action when something really has shifted.
Use control charts on any critical-to-quality output, key process input, or KPI being monitored over time. They are the standard tool for the Control phase of DMAIC.
Control charts and limits are central to SPC, which sits across the entire DMAIC cycle. They tie directly to capability indices (Cp, Cpk) and to the Six Sigma definition of "in control".
When the chart signals out-of-control, investigate the special cause immediately and document it. Re-baseline control limits only after the process has been improved and is stable — not as a routine reaction to every signal.
Pair control charts with capability indices, Pareto analysis and root-cause tools to convert SPC signals into structured improvement actions.
Statistically calculated boundaries on a control chart, usually three standard deviations either side of the process mean. They define the range of normal (common-cause) variation.
Spec limits define what is acceptable to the customer. Control limits define what is statistically normal for the process. The two are unrelated — a process can be in control but not capable, or capable but not in control.
A set of pattern-based rules that flag likely process shifts even when no single point breaches a control limit — e.g. seven points in a row on the same side of the centre line.
Only after a deliberate process change, and only once the new process is stable. Routine re-baselining masks drift and is one of the most common SPC mistakes.
Yes — Individuals charts (I-MR) handle one-at-a-time data. The calculation differs from X-bar R but the principle is identical.
Want to know how to use control limits to manage process variation? The Green Belt covers this in full.
View Green Belt →