SPC control charts are essential quality control tools. Operators use them to measure, regulate, and make manufacturing processes consistent. By controlling processes, they can diminish variations that can hurt quality.

Control charts help manufacturers decide if their processes are in statistical control. They tell operators when to act, and they show process behaviors by displaying variation. Control charts that show out-of-control processes serve as indicators that corrections or changes should be made to an organization’s process parameters. Ultimately, this results in process and product consistency.

Many manufacturers consider control charts to be the first sign of a root problem. However, choosing among the hundreds of available charts is not easy. The wrong chart could lead to false positives or overlook new process improvements insights.

Control charts are straightforward tools that help operators understand process variability. They do this by identifying four process states:

1) the ideal, 2) the threshold, 3) the brink of chaos and 4) the state of chaos

When a process functions in the ideal state, that process is in statistical control and creates total conformance. This process has demonstrated stability and target performance over time. It is predictable and it meets expectations.

A process that is in the threshold state is in statistical control but still yields intermittent nonconformance. This process will create constant nonconformances and displays low capability. It is still a predictable process, but it won’t consistently meet customer needs.

The brink of chaos state, however, shows a process that is not in statistical control. Yet, it still elicits defects. This process is unpredictable, but its outputs still meet customer desires. This process can generate nonconformances at any time.

The state of chaos is not in statistical control and yields irregular levels of nonconformance.

According to iSixSigma { https://www.isixsigma.com/tools-templates/control-charts/a-guide-to-control-charts/ }, every process falls into one of these states at any given time but will not remain in that state.

“All processes will migrate toward the state of chaos,” the author writes. “Companies typically begin some type of improvement effort when a process reaches the state of chaos (although arguably they would be better served to initiate improvement plans at the brink of chaos or threshold state).”

Control charts ultimately help manufacturers to notice when their processes are migrating in this direction. They can warn leaders and prompt them to get to the bottom of the variation, such as by performing a root cause analysis.

Here are some basic categories of control charts to choose from (although this is just a sampling).

  • Variables charts

    These charts measure variation on an endless scale and are more perceptive to change than attribute control charts, or charts those that measure variation on a finite scale.

  • Individuals charts

    These are handy when few measurements are available and when the natural subgroup is not yet known.

  • u– and c-charts.

    In a u-chart, a unit’s deficiencies must be independent of one another. A c-chart is preferable to a u-chart when there are a many possible defects on a unit, but there is only a small chance of any one defect taking place.

  • p– and np- charts

    These are helpful for charting proportions