Statistical Process Control & Operations | What is SPC? – Video & Lesson Transcript | Study.com

What is Statistical Process Control?

Statistical Process Control (SPC) is defined as a method of quality control that uses statistical methods to monitor and control product quality. SPC uses a data-driven approach to improve quality by eliminating unusual variations in the process being analyzed. These variations can be caused by many factors, including human error, machine error, or environmental factors. SPC can be used to monitor any process, including manufacturing processes, assembly lines, service operations, and even office work. SPC is usually used in conjunction with other quality control methods, such as Six Sigma.

Types of Variations

There are two types of variations that can occur in any process, common cause variation and special cause variation.

Common cause variation is caused by factors that are inherent to the process being monitored. These factors can include the type of materials used, the equipment used, the environment, or the natural variations that occur when humans are involved in the process. It is important to note that any process is bound to have a certain level of inherent variability. This is due to the fact that variation is a natural phenomenon; thus, it is impossible to eliminate all sources of variability. Common cause variation takes this inherent variability into account and aims to keep it within acceptable limits. For example, if the overall design of a product is causing various quality control issues that are not due to any specific individual or machine. Another example would be if the workers assembling a product are not working at their full potential due to the design of their workstation. In both of these cases, the root cause of the variation is not due to any special event or individual, but rather it is due to the inherent design of the process.

Special cause variation is caused by factors that are not inherent to the process being monitored or a specific event or issue. These factors can include human error, machine error, or outside influences, such as a series of extreme weather events. Special cause variation is usually easier to identify and eliminate than common cause variation. For example, if a specific machine is not functioning properly and is causing specific defects in a product. Another example would be if a single worker is not following the proper procedures. Therefore, causing extremely significant defects in large numbers of products. In both of these cases, the root cause of the variation is due to a specific event or issue that can be identified and addressed.

Statistical Process Control Example

As commonly known, variation is a natural phenomenon. Due to this, it is impossible to create a process that is free of all variability. However, it is possible to monitor and control the amount of variation in a process so that it remains within acceptable limits. This is where statistical process control comes in. SPC uses statistical methods to monitor process variation and identify when it is outside of acceptable limits. When this happens, corrective action can be taken to bring the process back into control.

One of the most common tools used in SPC is the control chart. Control charts are graphical representations of process data that are used to identify special cause variation. Control charts typically include three types of information:

• The data that was collected
• A center line that represents the mean or average of the data
• Upper and lower control limits that represent the acceptable limits of variation

Control charts are used to determine if a process is in statistical control. This means that the process is operating as it should and that the variation present is due to common causes. When a process is in statistical control, it is said to be predictable and stable. This predictability means that the process can be relied upon to produce consistent results within the acceptable limits of variation.

Suppose that a company is monitoring the weight of products coming off of an assembly line. They collect data for 100 products and create a control chart. The data shows that the average weight of the products is slightly below the desired weight and that the variation is within the acceptable limits. Based on this, the company can conclude that the process is in statistical control and is predictable.

Now assume that the same company collected data for 100 products a year later and found that the average weight was significantly below the desired weight. In addition, the control chart showed that the variation was outside of the acceptable limits. This would indicate that the process is not in statistical control and is not predictable. In this case, the company would need to take corrective action to bring the process back into control.

There are many different types of control charts that can be used to monitor different types of data. The type of control chart that is used will depend on the type of data being collected and the process being monitored. Some common types of control charts include:

• X-bar and R charts: These charts are used to monitor continuous data that can be measured on a scale. Examples of this type of data include length, width, temperature, etc.
• P-charts: These charts are used to monitor proportions or percentages. They are typically used to monitor the number of defects in a process.
• Np-charts: These charts are similar to P charts, but are used to monitor the number of non-conforming units in a process.
• C-charts: These charts are used to monitor the number of events that occur in a process. Examples of events include the number of defects, accidents, etc.

It is also important to mention the connection between SPC and the PDSA cycle. These two frameworks and methods are often used together to help improve quality and efficiency in a process. The PDSA cycle, also known as the Deming cycle, is an iterative four-step process that is used to plan, do, study, and act on improvements. SPC is used to monitor the process and identify when there is a problem. The PDSA cycle is then used to take corrective action and improve the process. The PDSA cycle steps are as follows:

• Plan: The first step is to develop a plan for how the process will be improved.
• Do: The second step is to implement the plan or process change and collect data.
• Study: The third step is to analyze the data to see if the process has improved. If a company has discovered that a change has reduced variation, then it must act.
• Act: The fourth step is to take action based on the results of the data analysis. This may involve making further changes to the process or implementing new controls. Also, because the PDSA method is cyclical, once the fourth step is complete, the cycle may start again at the first step of planning in order to continuously work on improvements.

The PDSA cycle is a continuous process that can be used to improve a procedure. This makes it a valuable tool for quality improvement. SPC and the PDSA cycle are often used together because they complement each other well. As previously stated, SPC can be used to identify problems and the PDSA cycle can be used to take corrective action.