Control Chart Generator

Generate Shewhart I-MR or X-bar R control charts from your data. Upload CSV/XLSX or paste values. Detects Nelson rule violations and calculates process capability.

Chart Settings

Data

What Is a Control Chart?

A control chart (Shewhart chart) is a time-series plot of process data with statistically calculated upper and lower control limits (UCL/LCL) set at ±3σ from the center line. Invented by Walter Shewhart at Bell Labs in the 1920s, it remains the foundational tool of Statistical Process Control (SPC) — distinguishing common-cause variation (inherent to the process) from special-cause variation (assignable to a specific factor).

I-MR vs. X-bar R

The I-MR chart (Individuals and Moving Range) is used when each observation is a single measurement — batch processes, destructive testing, or slow production. The X-bar R chart plots subgroup means and ranges, providing greater sensitivity to process shifts when rational subgroups of 2–10 consecutive measurements are available.

Nelson Rules

Beyond simple limit violations, Nelson rules (originally Western Electric rules) detect non-random patterns: runs of 9 on one side, trends of 6, oscillations of 14, zone violations, stratification, and mixture. This calculator checks all 8 rules to help identify special causes before they lead to defects.

Control Limits vs. Specification Limits

Control limits represent the voice of the process — what it actually does. Specification limits represent the voice of the customer — what it should do. A process can be in control but not capable (producing defects), or capable but out of control (drifting). Both dimensions matter: use control charts for stability, and capability indices like Cpk to measure how well the stable process meets specs.

Need ongoing SPC monitoring?

Svend's SPC module tracks control charts over time with automatic Nelson rule detection, Gage R&R, and capability trending — all connected to your quality workflow.

Try Svend Free

Frequently Asked Questions

What is a control chart?
A control chart (Shewhart chart) is a time-series plot with statistically derived upper and lower control limits (UCL/LCL). It distinguishes common-cause variation (inherent to the process) from special-cause variation (assignable to a specific factor). Points within the limits and showing no patterns indicate a stable, in-control process.
When should I use I-MR vs X-bar R?
Use I-MR when each observation is a single measurement — batch processes, destructive testing, or slow production. Use X-bar R when you can collect rational subgroups of 2–10 measurements taken close together in time, such as consecutive parts from a machine.
What are Nelson rules?
Nelson rules are a set of 8 decision rules for detecting non-random patterns in control chart data. Beyond limit violations (Rule 1), they detect runs, trends, oscillation, stratification, and mixture patterns, increasing the sensitivity of the chart to special causes.
What is the difference between control limits and specification limits?
Control limits (UCL/LCL) are calculated from the data and represent what the process is actually doing. Specification limits (USL/LSL) are set by engineering requirements and represent what the process should do. A process can be in control but not capable, or capable but out of control.
How many data points do I need for a control chart?
A minimum of 20–25 data points (or subgroups for X-bar R) is recommended to establish reliable control limits. Fewer than 20 points may produce unstable limits. Some Nelson rules require at least 15 consecutive points to detect.