You may have heard the term Six Sigma used in conjunction with lean manufacturing, a Kaizen approach or continuous quality improvement. Perhaps you thought Six Sigma only applied to large-scale business operations, or that newer philosophies had overtaken Six Sigma as the most updated approach to quality management? But if you're looking for a way to improve your production processes or solve a problem you’re having with quality, Six Sigma might be the answer. Are you and your team familiar with these concepts? Here's an overview.
Six Sigma is a method of quality improvement that relies heavily on data analytics to find the root cause of problems in the manufacturing, engineering or service process.
Most modern methods for continuous process improvement use a philosophy similar to the Six Sigma approach of eliminating waste or errors, no matter what name they go by today. In fact, many of the principles of Six Sigma are incorporated directly into ISO (International Organization for Standards). That’s why Six Sigma remains the gold standard for approaching process improvement in a data-centric, systematic way.
So what is Six Sigma?
In simple terms, Six Sigma is a structured, data-driven methodology for discovering and removing defects in a process – any process from manufacturing to engineering to services. Six Sigma gets its name from the idea of managing a process to stay within six standard deviations of the upper and lower limits of the mean (sigma is the statistical name for a standard deviation).
A bit of history of Six Sigma
The origins of Six Sigma are with Motorola and involve the adoption of a Japanese approach to quality management. In the early 1970s, Motorola experienced major quality problems with a line of television sets in which more than 10% of sales were used to fix errors and failures. The line was sold to the Japanese company Matsushita (later called Panasonic), which managed to turn the failure rate around after just three years and make the line profitable. They went from an error rate of 1.5 per manufactured device to 0.04 errors. The warranty costs decreased from $22 Million USD to $4 million USD. The number of employees needed for control and rework decreased from 120 to 15.
Naturally, the Motorola CEO, Robert Galvin, wanted to know how they did it. So his team visited the Japanese plant, studied their methods, and developed an improvement process based on the Japanese procedures that became known as Six Sigma. He said, “if they can do it, we can do it”.
Six Sigma uses a statistical approach to quantify how well a process is performing based on a specific set of expectations. An optimal result within Six Sigma means that a process doesn’t produce more than 3.4 defects per million opportunities. A defect is defined as anything that doesn’t match a specific set of customer specifications.
Six Sigma represents 6 standard deviations between mean and the upper and lower limits of acceptance.
DMAIC helps correct process problems
In Six Sigma, the data-driven quality strategy used to analyze and improve processes is known as DMAIC (Define, Measure, Analyze, Improve, Control). DMAIC what most people think of when they talk about using Six Sigma.
DMAIC is designed to uncover deviations and solve problems. It focuses on delivering the features or specifications the customer wants, and uses data and statistics to draw conclusions.
The Six Sigma DMAIC quality improvement process is divided into five different phases.
- Define. The first phase involves defining the problem and mapping it out. This includes describing the problem, setting a goal and determining what resources are needed to solve it.
- Measure. The second phase of DMAIC involves defining the project’s main metrics – describing the problem with numbers and determining the performance standards (limits for Y) and evaluating the measurement system.
- Analyze. In the third phase of DMAC, you look at data from your current process to see how stable or capable it is. Your operation or process must be able to produce results (products) that meet the specified requirements, so this is where you evaluate the standard deviation compared to the specification limits (tolerance limits).
- Improve. In this phase you’ll investigate how changes in X will impact the result and screen various potential causes to discover relationships (you’ll be using a Design of Experiments, DOE, approach here).
- Control. The focus of this phase is to ensure that the performance objective you identified in the Improve phase is well implemented and maintained.
Tools of Six Sigma
Six Sigma uses a number of analysis tools and methodologies to uncover and reduce variation in a process. The tools used may include:
- Fishbone Diagram – (also called an Ishikawa diagram) a visualization tool for categorizing the potential causes of a problem in order to identify its root causes.
- Pareto Chart – a type of chart that contains both a bar graph and a line graph. The individual values are represented in descending order by bars, and the cumulative total is represented by a line. It is used to analyze the frequency of problems or causes in a process.
- Affinity Diagram – a tool used organize ideas or topics into groupings based on their natural relationships. The Affinity process is often used to group ideas generated by brainstorming.
- Gage R&R (gage repeatability and reproducibility) – a statistical tool that determines the amount of variation in the measurement system arising from the measurement device and the people taking the measurement.
- Cause-and-effect matrix – risk assessment tool that helps identify critical steps in a process to determine if adequate controls exist to monitor and prevent adverse events
- Risk matrix – a risk assessment tool used to assess and score risks on various levels to determine which are most likely and which have the most significant impact
- Failure mode and effects analysis (FMEA) – helps evaluate the risk associated with steps in a process or with the steps in the implementation plan of any project and provide a risk priority score.
- Design of Experiments - a systematic, rigorous approach to problem solving that uses data to determine cause and effect relationships when making engineering or design decisions
Fishbone (or Ishikawa) Diagram is a quality improvement tool used to structure the problem to help identify and uncover the potential factors and causes of error in a process.
A Pareto chart, named after Vilfredo Pareto, is a type of chart that contains both individual bars and a cumulative line graph. The graph can be used for identifying factors that might be causing defects. Identified factors can be further investigated to determine if they are the root cause of the problem.
A screening DOE is a tool used in the fourth step of the DMAIC process, the Improve stage. DOE is used to plan maximally informative experiments or process run conditions. To learn more on DOE, please watch this webinar.
How are Six Sigma, Lean and Kaizen related?
Lean is a process improvement methodology that focuses on reducing waste and is often used closely with the tools of Six Sigma to increase efficiency and improve business processes. Its origins lie in the Toyota Production System of Just In Time production, which took ideas from the manufacturing techniques of Henry Ford and the Statistical Quality Control ideas of Edwards Deming.
Kaizen is the Japanese word for “improvement.” Kaizen is a process of continuous improvement aimed at eliminating waste (defined as the three Mus: Muda (waste), Mura (defect/variation), and Muri (strain on staff and machinery). Kaizen focuses on small incremental changes gradually over time to reduce waste and improve efficiency. This term is often used in conjunction with Lean manufacturing.
When should you use Six Sigma?
Six Sigma and DMAIC are powerful tools that use statistical methods to help you uncover problems in your processes. Knowing when to apply Six Sigma will help make the process more effective when you use it. Implementing DMAIC as your improvement process will require commitment and support from management and training of key resources.
Not all process problems require the full implementation of DMAIC, however. Some can be solved with a brainstorming session or a Root Cause Analysis. You can try using the Five Whys method. (Asking a series of five Why? Questions). It looks something like this (in a simplified format):
- Why is the product failing? Faulty material.
- Why is the material faulty? Impurities.
- Why does the material have impurities? Dust in the air.
- Why is there dust in the air? No air filters.
- Why are there no air filters? No budget.
Solution: Budget for air filters.
But if it’s a problem that keeps recurring, or you've tried to solve it before and haven’t been successful, DMAIC and Six Sigma may be the solution.
When to use Six Sigma
In short, you may want to consider using Six Sigma for:
- A complicated problem
- A problem that keeps popping up (previously “solved” but returns)
The Umetrics Suite of Data Analytics tools are uniquely designed to help you manage analytics and uncover the details in your data.
We’ll go into more details on how Umetrics Suite fits into the DMAIC process in our next blog.
Take our quick poll
Want to know more about Six Sigma?
Watch this recorded webinar.