Using the Seven Basic Quality Tools
What are the seven basic quality tools?
There are several basic quality tools every data explorer should have in their toolbox, in addition to the control chart. Also known as the old seven, the first seven, the basic seven, the classic seven, and the seven quality control tools, these tools are simple yet effective. They can help visualize your data -- so you can see them more clearly -- and help identify patterns, trends, and problems in need of your attention.
Using basic quality tools: A case study
Imagine you work in a manufacturing plant that produces widgets using an injection molding process. Recently, the scrap rate has become too high for the business to remain profitable. Your team needs to answer the following questions:
- What types of defects occur most often?
- When and where are these defects happening?
- What might be causing the defects?
To solve this problem, you can use the basic quality control tools. These tools help you collect data, visualize them, and analyze them so you can identify patterns and uncover potential causes. Examples are shown using JMP statistical software.
Quality tool #1: Run chart
What it does: A run chart tracks data over time to identify trends or patterns.
How it helps: It can show if defects are increasing or decreasing over time or if they occur in specific, repeatable patterns.
In practice: The team initially thought that the defects would show up in a run chart of either Pressure or Time, so they tracked both factors for 100 runs.
After not coming to any useful conclusions from this first run chart, they decided to track three additional factors: Defect Type, Shift, and Cavity. The team monitored results over the next 100 runs using a modified run chart, this time switching to a bar chart format. Using color and features like the Column Switcher in JMP, the team noticed that Cavity 3 is creating all the Short Shot defects.
Quality tool #2: Histogram
What it does: A histogram displays the distribution of data to show how often different values occur.
How it helps: It can reveal the most common defect measurements or values, helping you understand the variation in your process.
In practice: Interactive selection makes it easier to ask questions and draw conclusions. The histogram below shows that defects are not restricted to one Shift. Rather, Cavity 3 is creating the Short Shot defects for every shift.
Quality tool #3: Check sheet
What it does: A check sheet is a simple tool for collecting and organizing data.
How it helps: In the widget example, a check sheet can be used to record the type and frequency of defects as they occur.
In practice: While check sheets are generally made by hand, some software (like JMP) can also create them from existing data. In the example below, you’ll notice that Short Shot shows up as the most common Defect Type.
Quality tool #4: Pareto plot
What it does: A Pareto plot highlights the most frequent causes of defects by sorting data in descending order and adding a cumulative percentage curve.
How it helps: A Pareto plot can show which defect types are the most frequent, helping you focus on the issues that have the biggest impact.
In practice: Using the Column Switcher in JMP can make diagnosing a problem much easier. In the example below, you’ll quickly notice that the most common defect is restricted to just one Cavity but occurs on all three levels of Shift.
Quality tool #5: Fishbone diagram (cause-and-effect diagram)
What it does: A fishbone diagram identifies potential causes of a problem by categorizing them into groups (e.g., People, Methods, Materials, Machines).
How it helps: A fishbone diagram can help you brainstorm possible reasons for defects. Once the list has been created, each item on the list can then be investigated. Fishbone diagrams also help you move beyond the simple cause of a problem to find its root cause.
In practice: In the example below, you’ll see how the fishbone diagram helped a problem-solving team determine that they first want to investigate the thermocouple near Cavity 3.
Quality tool #6: Scatter plot
What it does: A scatter plot shows the relationship between two continuous variables.
How it helps: A scatter plot can reveal if there is a correlation between defect rates and another factor, such as machine speed or temperature.
In practice: In the example below, you’ll notice that the temperature of Cavity 3 has a strong relationship with the number of Short Shot defects created per hour, but the Ambient Humidity has no relationship with these defects.
Quality tool #7: Control chart
The final quality tool is the control chart . A control chart is a run chart with the addition of control limits that are calculated from the natural variation of the process. Some control chart types include:
- X-MR charts
- Xbar-S or Xbar-R charts
- Control charts for counting attributes
- CUSUM control charts
- EWMA control charts
- Multivariate control charts
Why use these tools
The basic quality tools we’ve shared above are simple yet powerful. They help teams visualize data clearly and identify patterns and trends. Once teams identify these patterns, they can use the tools to focus on the most critical issues and investigate potential causes of problems. In our example above, a team was able to trace a significant yield issue to a heating problem with a specific cavity in their injection process. Being able to trace this problem quickly helped the company a) fix the heating problem and b) implement a more frequent preventative maintenance schedule to verify the heating systems for each cavity, thus preventing the problem from recurring in the future.