Why applying Statistical Process Control (SPC) can be a business differential? Check it out!

The control phase of the DMAIC method aims to monitor the results achieved after the implementation of the improvements, establish controls that ensure the sustainability of the results, define the "process owner" and how the process will be monitored on a daily basis.

The estimated time for this stage of the Lean Six Sigma project is approximately 2 to 4 weeks. And its main tools are: Control Charts, OCAP, Standard Operating Procedure and Poka Yoke.

But do you know what a Statistical Process Control Chart is? Or what SPC is in this context? Do you also know what it is for and how to do it? If you answered no to any of these questions, keep reading this post to find out.

In this article you will learn:

• What is Statistical Process Control?
• What is the importance of SPC?
• How to follow up the Statistical Process Control?
• How to analyze a Statistical Process Control?

What is Statistical Process Control?

Statistical process control, also known as SPC, is a quality tool that can be defined as a method for preventing and detecting defects/problems in evaluated processes.

It was developed by Walter Shewhart in the beginning of the 20th century and spread around the world in the 1960s by Edwards Deming with the application in the PDCA cycle.

CEP is a study that aims to monitor a product or service during its production process, in order to identify the non-compliant outputs, so that the root cause can be eliminated and the process is stabilized, preventing further variations from occurring.

Every process has small variations, and we can classify them into two groups:

Causes of common variations: These are random and unavoidable variations that occur within certain limits, without a systematic cause that can be eliminated.

Special causes of variation: This occurs when the process exhibits systematic deviations or variations outside its limits, as a consequence of clearly identifiable reasons within the process that can be eliminated.

What is the importance of statistical process control?

The importance of statistical process control is undoubtedly to have a holistic view of the process. But why control a process? The answer to this question is given with another question: What can be said about an unstable process? Very little! And that is why we must control processes.

If there are special causes of variation, the process output is not stable and is not predictable over time. Therefore, we have no way of knowing what will happen tomorrow, for example. So we will have control charts like this.

If only the common causes of variation are present, the output of a process forms a distribution that is stable and predictable over time. Thus generating graphs that look like this.

Control helps maintain the improvements achieved, and sets a new benchmark for best practices.

Are you tired of missing out on incredible career opportunities because you don't know about the main Excel tools?

So you are in the right place! In the Excel for Beginners course, you will learn to work with data in an agile way.

In addition, the course is available for FREE, just click on the banner button below and embark on this journey of knowledge!

How to analyze a Statistical Process Control?

To analyze statistical process control, you must evaluate control charts. Below, you will learn more about them.

What are control charts?

The control charts are nothing more than a set of points (samples) ordered in time, which are interpreted as a function of horizontal lines, called UCL (Upper Control Limit) and LCL (Lower Control Limit).

They are designed for data with normal or approximately normal distributions. They are tools for monitoring variability and evaluating process stability.

Through Control Charts, we can distinguish the action of common causes and special causes in the process.

With the process presented in this example, we can observe that it is subject only to common causes and is therefore considered stable and predictable. We say that the process is under statistical control.

The statistical theory developed by Shewhart for calculating the control limits is based on the idea of the normal distribution, and since the process is stable, the sample data will have a probability very close to 100% of being within -3 sigma to +3 sigma from the population mean.

There are 5 tests that must be performed to find that a process is non-compliant. This indicates a potential special cause acting on the process and consequently shows the need for the series of points to be investigated. These tests are:

1.Points outside Control Limits:

One or more points cross the LCL or UCL lines.

2.Periodicity:
The plotted curve repeatedly shows an upward and downward trend at similar amplitude time intervals.

3.Sequence:

Seven or more consecutive points appear on only one side of the midline.

4.Trend:

Seven or more consecutive points show a continuous upward or downward movement.

5.Approaching the Control Limits:
Occurrence of two, of three consecutive points, between the +2 sigma and +3 sigma lines, or between the -2 sigma and -3 sigma lines.

You can still use the control chart to decrease the process variation more and more, by decreasing the variation of the control limits and analyzing the causes of instabilities.

You can use tools such as the Ishikawa diagram to find root causes and the 5W2H to develop action plans.

Several times we get lost in so many Excel functions, and we don't know where to start and what to learn. To help you, we created the First Steps eBook in Excel to guide your practice with the tool, as well as how and where to learn about its most complex resources. Learn how to solve everyday problems quickly and efficiently in Excel.

By downloading our eBook, you will learn the first steps to create your spreadsheets and use their basic and essential functions.

Let's get started?