what is a control chart in six sigma

Understanding Control Charts in Six Sigma

By Michael Rodriguez
AD

In the realms of statistical process control andSix Sigma methodology, a control chart stands as a formidable tool that offers a visual representation of process stability and capability. It's a powerful visual aid that helps identify if a process is in control or out of control, thereby aiding in process improvement and quality control. But what exactly constitutes a control chart in the context of Six Sigma?

Put simply, a control chart in Six Sigma is a tool designed to monitor and analyze the variation in a process over time. It's a graphical representation of data plotted on a graph with a centerline, upper control limit (UCL), and lower control limit (LCL), which are typically set at three standard deviations from the mean. The data plotted in the chart could be anything from product measurements, such as weight or dimension, to process data, like temperature or pressure. If the data points fluctuate within these limits, the process is considered under statistical control, but if not, it indicates that a special cause of variation is at play.

The Building Blocks of a Control Chart

A well-constructed control chart comprises several key components. Understanding these is integral to interpreting and using a control chart effectively in the Six Sigma context.

AD
What is Six Sigma? Six Sigma Levels | Methodology | Tools
What is Six Sigma? Six Sigma Levels | Methodology | Tools
Control Charts Excel | Control Chart Software | Shewhart Chart
Control Charts Excel | Control Chart Software | Shewhart Chart
the six sigma statistics are shown in blue and green, as well as an upward
the six sigma statistics are shown in blue and green, as well as an upward

primordial among them is the centerline, which is a graphical representation of the average of the data. It serves as the reference point for assessing the stability of the process. Next, the upper and lower control limits, as previously mentioned, define the acceptable range of variation for the process. A process is considered stable and in control when all the data points fall within these limits.

The Role of Standard Deviation (σ)

Standard deviation, commonly denoted as 'σ', is a cornerstone of control charts in Six Sigma. It measures the amount of variation or dispersion in a set of values. In control charts, it's used to calculate control limits, which are typically set at ±3σ from the mean. This boundary, often referred to as the '3-sigma rule', is based on statistical probabilities; approximately 99.73% of the data will fall within this range assuming the process is normally distributed and under statistical control.

DMAIC process management as six sigma strategy key factors outline diagram
DMAIC process management as six sigma strategy key factors outline diagram
DMAIC Framework Six Sigma
DMAIC Framework Six Sigma
an image of a diagram with the names and numbers for each project, including several different types
an image of a diagram with the names and numbers for each project, including several different types

Therefore, a process that operates within these control limits 99.73% of the time can be considered stable and predictable. This means that any data point, or more frequently, a pattern of data points, that falls outside these control limits is likely to be caused by a special, assignable cause. Identifying and addressing these special causes is a key aspect of Six Sigma methodology.

The Mean (X̄) and Range (R)

The mean (X̄) is a fundamental measure of central tendency used to calculate the centerline on a control chart. However, it's not the only measure of central tendency that can be used. The median and mode are other examples. The range (R), on the other hand, is another measure of variability that is as easy to calculate as it is to understand. It's simply the difference between the largest and smallest values in a data set. This measure of variation is used when the sample size is small enough that the data set's distribution may not adequately resemble the normal distribution.

AD

In the context of control charts, the range can be used as an alternative to standard deviation to calculate control limits, particularly when the sample size is less than about 25. This is because the range is a simple and efficient measure of variability that requires minimal computation when compared to standard deviation. However, it's important to note that the range has limited flexibility when it comes to large data sets or skewed distributions.

an info sheet with information about the six sigma characters
an info sheet with information about the six sigma characters
a line graph shows the different stages of an upper control limit
a line graph shows the different stages of an upper control limit
four diagrams showing the different types of graphs and their corresponding points, with one line going up
four diagrams showing the different types of graphs and their corresponding points, with one line going up
a line graph showing the control chart with stabily and unstable points for each trend
a line graph showing the control chart with stabily and unstable points for each trend
Six sigma techniques and tools for process improvement outline collection set
Six sigma techniques and tools for process improvement outline collection set
the six sigma formulas are shown in red and green, with numbers on each
the six sigma formulas are shown in red and green, with numbers on each

Types of Control Charts in Six Sigma

A variety of control charts exist, tailored to different scenarios and types of data. Here, we'll briefly explore a few common types of control charts used in Six Sigma.

At the heart of many control charts is the X-bar and R chart. This pair of charts is used for attribute data and is particularly useful for small sample sizes. The X-bar chart monitors the process mean, while the R chart monitors the process variability using the range.

AD

The Individuals and Moving Range (XMR) Chart

When dealing with just a single measurement at a time, or when samples are too small to calculate statistics like range or standard deviation, an Individuals and Moving Range (XmR) chart can prove useful. This two-chart combination plots each individual sample against a moving range, which is calculated as the difference between two consecutive samples. This chart is versatile and can be used to monitor both variables and attributes.

The p, np, c, and u charts focus on attributes data, rather than variables. The p chart, for instance, monitors the proportion of defective items, making it useful in scenarios where I=100% inspection is not feasible. The np chart, on the other hand, monitors the number of defects in a sample, and so on.

In conclusion, understanding and applying control charts in the Six Sigma methodology requires a combination of statistical knowledge, practical experience, and a systematic approach towards continuous process improvement. Embracing control charts as a tool for understanding and mitigating process variation ultimately leads to improved product and process quality. So, whether you're a seasoned Six Sigma professional or just starting out, remember, the journey towards quality excellence begins with a control chart.

AD
AD