Every process is designed to generate output – either a product or a service. In addition to this, processes generate a lot of data as well. Statistical Process Control or SPC is a statistical method of using the data generated by a process to control and improve it continually.

What is Statistical Process Control?

The term “statistical process control” (SPC) refers to the application of statistical methods for process or production method control.

It is a quick strategy to support ongoing improvement. When regularly monitored and regulated, managers can ensure a process that operates at its best potential and produce consistent, high-quality manufacturing.

Operations Manager or Auditor? Your Choice

Lean Six Sigma Green Belt Training Course

Explore Program

Why Use Statistical Process Control?

The application of SPC principles and continuous improvement go hand in hand. SPC, or statistical process control, is a method that’s frequently used to find production-line flaws and guarantee that the finished product falls within accepted quality limits. 

As its name implies, it largely relies on statistical approaches to provide you with a comprehensive picture of the present state of your production facilities. Yet, when used correctly, it can be a very effective tool for increasing output and minimizing different types of waste.

Statistical Process Control Benefits

A product’s performance consistency according to its design parameters is measured through statistical process control or SPC. Some of the advantages manufacturers can experience include the following.

• Less Warranty, Rework, and Scrap Claims
• Greater Productivity
• Better Use of Resources
• Improved Operational Effectiveness
• Fewer Manual Inspections
• Increased Customer Satisfaction
• Reduced Costs
• Detailed Analyses and Reporting

SPC tools help track process behavior, identify problems with internal systems, and resolve production-related issues. There are 14 SPC tools employed: 7 quality control tools and 7 supplementary tools.

What are SPC Charts?

A statistical process control system (SPC) is a method of controlling a production process or method utilizing statistical techniques. Monitoring process behavior, identifying problems in internal systems, and finding solutions to production problems can all be accomplished using SPC tools and procedures.

An SPC chart is used to study the changes in the process over time. All the data generated from the process are plotted in time order. The three main components of an SPC chart are – a central line (CL) for the average, a lower control line (LCL) for the lower control unit, and an upper control line (UCL) for the upper control unit. 

Fig: Sample SPC Chart (Source)

SPC charts were initially developed by Dr. Walter A. Shewhart of Bell Laboratories in the 1920s. This is why they are also known as Shewhart charts. However, they were made popular by Dr. W. Edwards Deming when he introduced the concept to the Japanese industry after World War II. Nowadays, SPC charts have been incorporated by organizations around the world as one of the primary tools to monitor and improve the control of a process.

What are Control Limits?

Control limits are the standard deviations located above and below the center line of an SPC chart. If the data points are within the control limits, it indicates that the process is in control (common cause variation). If there are data points outside of these control units, it indicates that a process is out of control (special cause variation).

Fig: Control limits of an SPC chart (Source)

It is best to plot the data points manually in the early stages of making an SPC chart. Once the formulas and meaning is understood, you can use statistical software to update them. There are a number of tests that are used to detect an “out of control” variation. Some of the most popular ones are Nelson tests and Western Electric tests.

Lead Projects with Strategic Data Interpretation

Lean Six Sigma Green Belt Training Course

Explore Program

How to Implement SPC Charts? 

SPC charts require organization commitment across functional boundaries. Here is a step by step process on how you can construct an effective SPC chart:

Step 1: Determine an Appropriate Measurement Method

The first step is to decide what type of data to collect – variable or attribute. It is highly advisable to use variable data wherever possible as it provides a higher quality of information. Once you decide what type of data to collect, you can then choose the appropriate control chart for your data.

Step 2: Determine the Time Period for Collecting and Plotting Data

Because SPC charts measure the changes in data over time, it is necessary that you maintain a frequency and time period to collect and plot the data. For example, making an SPC chart every day or every other week can help you see whether your process is reliable and improving constantly or whether you will be able to meet quality standards in time.

Step 3: Establish Control Units 

The next step in creating an SPC chart is to establish the control units. Here is how you can calculate the control units:

• Estimate the standard deviation (σ) of the sample data
• To calculate UCL, 

UCL = average + 3 x σ 

• To calculate LCL,

LCL = average – 3 x σ

Step 4: Plot Data Points and Identify Out-Of-Control Data Points

After establishing control limits, the next step is to plot the data points on the SPC chart. Once you’ve plotted the data points, you can start to see patterns in them. Recognizing these patterns is the key to finding the root cause of special causes. Some of these patterns depend on certain “zones”.

Fig: Sample SPC chart with zones (Source)

Here are the eight rules used to identify an out-of-control condition.

Rule

Rule Name

Pattern

1

Beyond Limits

One or more points beyond the control limits

2

Zone A

2 out of 3 consecutive points in Zone A or beyond

3

Zone B

4 out of 5 consecutive points in Zone B or beyond

4

Zone C

7 or more consecutive points on one side of the average (in Zone C or beyond)

5

Trend

7 consecutive points trending up or trending down

6

Mixture

8 consecutive points with no points in Zone C

7

Stratification

15 consecutive points in Zone C

8

Over-control

14 consecutive points alternating up and down

Step 5: Correct Out-Of-Control Data Points

Whenever you find any data points lying outside the control limits, mark it on the chart and investigate the cause. Also, document what was investigated, the cause that led to it being out of control and the necessary steps taken to control it. You can use a corrective action matrix to identify responsibilities and set target dates to track the actions taken.

Quality Engineer or Quality Analyst? Your Choice

Lean Six Sigma Green Belt Training Course

Explore Program

Step 6: Calculate Cp and Cpk

The next step is to calculate Cp (capability) and Cpk (performance) to determine whether the process is able to meet specifications.

Cp is calculated as

And Cpk is calculated as 

where,

• X = process average
• LSL = Lower Specification Limit
• USL = Upper Specification Limit
• σest = Process Standard Deviation

Step 7: Monitor The Process

The last step is to continually monitor the process and keep updating the SPC chart. Regular monitoring of a process can provide proactive responses rather than a reactive response when it may be too late or costly.

Uses of SPC Charts

SPC charts are used for continuous improvement of a process using a number of techniques. There are a number of ways SPC charts can help business analysts, but the most important ones are as follows:

• Find and correct problems as soon as they occur
• Predict the expected outcomes of a process
• Determine whether a process is in a stable condition
• Provide information on which areas to prioritize on to improve the process

Cause and Effect Graphs

Since their creation by Kaoru Ishikawa created in 1943, they are also known as Ishikawa diagrams. However, because of their resemblance to a fishbone, they are also known as fishbone diagrams.

The graphic illustrates the connections between several factors of the impact under consideration. Brainstorming is organized using this tool. Many reasons for every issue can be found using cause-and-effect diagrams.

Histograms

A histogram is a visual representation of how the outputs of a product or process vary. Histograms aid in process analysis and demonstrate the capabilities of a process. They display frequency distributions and have the appearance of bar charts. For numbered data, they are perfect.

Pareto Graphs

Pareto charts are used to visually display categories of issues so they can be correctly prioritized. A Pareto chart shows the percentage of the overall problem that each minor problem contributes to, indicating which issue should be addressed first. 

Pareto charts are especially helpful in gauging the frequency of issues. They demonstrate the Pareto principle of 80/20, which states that focusing on 20 percent of the processes will solve 80 percent of the problems.

Probability Plots

The probability plot is a graph of the total relative frequencies of the data, shown on a standard probability scale. If the data is normal, it will create a fairly straight line.

A probability plot helps analyze data for normalcy, but it is especially helpful in assessing the capability of a process when the data are not normally distributed.

Control Charts

These statistical process tools are the most well-known and the oldest. Control charts use graphics to explain how a process’s variability changes over time. They can reveal irregularities and irrational variations when used to track the operation.

Scatter Diagrams

Scatter diagrams help locate potential cause-and-effect connections. They can demonstrate the link between two variables and how strongly they are related. However, it cannot show causation between variables.

Check List

A checklist is a systematically prepared form for data collection and analysis. It is a general-purpose data collection and analysis tool that may be used for various tasks.

Data Stratification

Stratification is the process of classifying information, people, and things into separate categories or levels. It is a method used in conjunction with other data analysis tools. This tool makes it easier to identify patterns in data and is ideal for storing data from several sources.

Defect Maps

These maps show and track a product’s problems, concentrating on its physical locations. The maps show each flaw in detail.

Event Logs

These are standard recordings that capture significant hardware and software events.

Process Flowcharts 

Process flowcharts visually represent the different steps of a process, presented in the order they occur.

Progress Centers

Progress centers are centralized sites that let organizations monitor progress and gather data when choices need to be made.

Randomization

This tool or process randomly allocates manufacturing units to a treatment group.

Sample Size Determination

This tool refers to selecting how many individuals or events to include to produce a statistical analysis.

Learn Six Sigma and Get Upto USD 114600 PA

Lean Six Sigma Green Belt Training Course

Explore Program

History of Statistical Process Control (SPC)

Quality control has been present for a long time. The statistical method is among the most effective instruments in the statistical quality process. Walter A. Shewhart created SPC at Bell Laboratories in 1920.

After that, H.F. Dodge and H.G. Romig, two other Bell Labs statisticians, led initiatives to apply statistical theory to sampling inspection. Most of the current philosophy of statistical quality and control is based on the work of these three pioneers.

SQC Vs SPC

SPC and SQC both contribute to offering efficient output and ideal outcomes by facilitating smooth operations. They both support the overall success of operations, yet their respective duties are distinct.

SQC (Statistical Quality Control) refers to using statistical and analytical methods to track the results of a process. On the other hand, SPC (Statistical Process Control) uses the same instruments to regulate process inputs. 

While both SPC and SQC have a place in a facility, choosing the appropriate parameters to monitor at the appropriate times is crucial. The distinction is in the use of strategy.

Here’s What You Should Do Next

SPC charts are one of the starting points for any Lean Six Sigma project. As such, it is important to understand these statistical control charts well to keep a process under control. If you are interested to learn more, you can start off with Simplilearn’s Certified Lean Six Sigma Green Belt online program. This course integrates lean and the DMAIC methodology with case studies to provide you the skills required for an organization’s growth.

FAQs 

1: What is an example of statistical control?

Statistical control is applied to any process wherein conforming with product specifications is required, and the output can be measured. An example of statistical process control is its application in manufacturing lines.

2: What is statistical control in statistics?

Statistical process control, abbreviated as SPC, is the usage of statistical approaches to regulate a process/ production method. SPC tools help monitor process behavior, find issues in internal systems, and discover solutions for production problems.

3: What are the three basics of statistical process control?

The three essential components of a statistical process control chart include a central line (CL) for the average, an upper control line (UCL) for the upper control unit and a lower control line (LCL) for the lower control unit.

4: What are SPC charts?

SPC or Statistical Process Control charts are simple graphical tools that assist process performance monitoring. These line graphs show a measure in chronological order, with the time/ observation number on the horizontal (x) axis and the measure on the vertical (y) axis.

5. Which software is used for SPC?

One of the popular software for data analysis and quality improvement is Minitab. Real-Time SPC powered by Minitab provides real-time capabilities and trusted analysis for process monitoring in a comprehensive solution.