SPC Tool
OVERVIEW
Control charts help you to monitor process stability over time so that you can identify and correct instabilities in a process.
In the SPC tool, you can create eight different control charts based on the data that you want to graph:
- I-MR Chart – monitor the mean and variation of your process when you have continuous data that are individual observations not in subgroups.
- Xbar-R Chart – monitor the mean and variation of a process when you have continuous data and subgroup sizes of 8 or less.
- Xbar-S Chart – monitor the mean and variation of a process when you have continuous data and subgroup sizes of 9 or more.
- I-MR-R/S Chart – monitor the mean of your process and the variation between and within subgroups when each subgroup is a different part or batch.
- P Chart – monitor the proportion of defective items where each item can be classified into one of two categories, such as pass or fail.
- NP Chart – monitor the number of defective items where each item can be classified into one of two categories, such as pass or fail.
- U Chart – monitor the number of defects per unit, where each item can have multiple defects.
- C Chart – monitor the number of defects where each item can have multiple defects. You should use a C chart only when your subgroups are the same size.
TOOLBAR
1. Hide / Show
Click to Hide/Show the Setup pane.
2. Reset
Clear/Refresh the entries in the Setup pane.
3. Save
Save the control chart that you created, along with the settings used to create it. Give your control chart a descriptive name. Optionally, you can add a description and specify if you want to share the control chart with other users.
4. Run
Click to generate a control chart after you have completed the fields in Setup and any optional fields in Option(s).
5. Save External
After you have saved your control chart, you can share it externally to a Dashboard or URL.
6. Export to Minitab
Create a worksheet of the data to open in Minitab. In Version:
- Choose Minitab 18 to create an MTW file to use in Minitab 18 or earlier.
- Choose Minitab 19 to create an MWX file to use in Minitab 19.
SETUP
SETUP tab
In the Setup tab, you identify which control chart you want to create and which tests to perform to detect any special causes in your process.
1. Configuration
Choose to use the current configuration of the data or a saved configuration. For more information on configurations, go to What are the Configuration Elements in the Prep Tool?
2. Control Chart
Choose the control chart that you want to create:
- I-MR
- Xbar-R
- Xbar-S
- I-MR-R/S
- P Chart
- NP Chart
- U Chart
- C Chart
3. Plot
Choose the column of data that you want to display on the control chart.
4. & 5. Subgroup Sizes and Field/Value
(Applies to Xbar-R, Xbar-S, I-MR-R/S, P, NP, and C charts)
For charts that include subgroups, you can either enter a column of data that identifies which subgroup each measurement is from, or enter a value if all subgroups are the same size.
1. To enter a column of subgroup size values, in Subgroup Sizes, select By Field;
in Field, enter the column of subgroup ID values.
2. To enter a constant value, in Subgroup Sizes, select By Value;
in Value, enter the subgroup size (must be a positive integer that is greater than or equal to 2).
6. Test(s)
Tests for special causes are available to determine which observations to investigate, and to identify the specific patterns and trends in your data. By default, Test 1 is the only test used. Select additional tests based on company or industry standards.
You can make each test more or less sensitive by changing the value of K.
Tests 1-8 are available for I-MR, Xbar-R, Xbar-S, and I-MR-R/S charts.
Tests 1-4 are available for P, NP, C, and U charts.
Test 1
- Identifies subgroups that are unusual (compared to other subgroups).
- Test 1 is universally recognized as necessary for detecting out-of-control situations.
- If small shifts in the process are of interest, you can use Test 2 to supplement Test 1 to create a control chart that has greater sensitivity.
Test 2
- Identifies shifts in the process centering or variation.
- If small shifts in the process are of interest, you can use Test 2 to supplement Test 1 (to create a control chart that has greater sensitivity).
Test 3
- Test 3 detects trends.
- This test looks for a long series of consecutive points that consistently increase in value or decrease in value.
Test 4
- Test 4 detects systematic variation.
- You want the pattern of variation in a process to be random, but a point that fails Test 4 might indicate that the pattern of variation is predictable.
Test 5
- Test 5 detects small shifts in the process.
Test 6
- Test 6 detects small shifts in the process.
Test 7
- Test 7 detects a pattern of variation that is sometimes mistaken as evidence of good control.
- This test detects control limits that are too wide.
- Control limits that are too wide are often caused by stratified data, which occur when a systematic source of variation is present within each subgroup.
Test 8
- Test 8 detects a mixture pattern.
- In a mixture pattern, the points tend to fall away from the center line and instead fall near the control limits.
OPTION(S) tab
In the Option(s) tab:
- You can specify how much data to display on your control chart.
- You can change line colors and/or specify how to calculate the Upper Control Limits (UCL), Center Line, and Lower Control Limits (LCL).
- You can also include additional reference lines.
1. Calculation Method and Subgroups To Display
Calculation Method
By default, the parameters of control charts are calculated using all your data. However, you may want to use historical data in the calculations or omit some subgroups or observations from your current data due to special causes that you have already corrected.
To create the subset of data, use the Prep tool to create the data that you want to use to calculate the control limits. Then under Calculation Method, choose Subset (View). In View, choose the data that you want to use in the calculations.
Subgroups To Display
For large data sets, you may want to limit the amount of data that is displayed on your control chart. In Subgroups To Display, enter a positive integer to specify the number of data points to display on the control chart based on the most recent data. For example, if you enter 30 as the limit, only the most recent 30 subgroups or observations are displayed. Leave this field blank if you want to display all subgroups on your control chart.
2. Series Plot Lines
Control charts include an Upper Control Limit (UCL), a Center Line, and a Lower Control Limit (LCL).
The Center Line represents the process mean. The Control Limits represent the process variation.
By default, the Control Limits are drawn at distances of 3σ above and below the Center Line.
Color
To change the color for the connect line (that connects the plotted points), click under Color and choose a different color.
On/Off Visibility toggle
Click the Eyeball icon to toggle On/Off the visibility of that line on the control chart.
The Eyeball icon with a line across it indicates that the line will not be shown on the chart.
Advanced Options icon
Click the Advanced Options icon to modify how the Lines are calculated and displayed:
For control charts that display multiple charts (for example, I-MR-R/S), you can customize the Connect Line, UCL, Center Line, and LCL (for each chart).
3. Add Plot Line
To add a reference line or additional sigma limits to your control chart, click the Add Plot Line button. A custom line will be added to the series. Click the Advanced Options icon to specify the value for the line and its color and style. If you want to denote any points that fall above or below this custom line, in Mark Points, choose either Below Value or Above Value. In Mark Color, you can specify a color for the points that fall above or below the custom line.
SAVE(S)
Go to the Save(s) tab to view and access your saved control charts.
This example shows 3 saved control chart views, and the 3 action icons (for options with each of the control charts).
1. RUN
Click to run the control chart.
2. EDIT
Click to edit the setup for running a control chart.
3. REMOVE
Click to delete a control chart.
SETTING AN ALARM
Click the Alarm(s) icon in the upper right to set an Alarm or view existing Alarm(s).
Use Alarm(s) to get notifications about when a point fails a test for special causes so that you can investigate issues as soon as they occur.
Alarm(s) can be sent via Email, Text Message, Notifications, or through a URL.
COLLABORATIVE SPACE
Click the Collaborative Space icon in the upper right to Open/Close the Collaborative Space.
Here you and your colleague(s) can add Notes or Issues about specific points on your control chart.
SHARING YOUR CONTROL CHART
Click the Save External icon in the upper left to share your control chart to a dashboard.
1. Name the control chart that you will be sharing externally.
2. Select the Dashboard from the menu.
3. Copy/Paste the Web URL to share it externally.
4. Click Save.
The control chart "Web URL" options
To download your control chart, click the menu icon in the upper right of the control chart.
You can download the control chart as a PNG, JPEG, PDF, or SVG.
METHODS AND FORMULAS
Click the below links to access Minitab’s Help topics for the methods and formulas for the control charts.
I-MR chart
Methods and formulas for I chart
Methods and formulas for MR chart
Xbar-R chart
Methods and formulas for Xbar chart
Methods and formulas for R chart
Xbar-S chart
Methods and formulas for Xbar chart
Methods and formulas for S chart
I-MR-R/S chart
Methods and formulas for I chart
Methods and formulas for MR chart
Methods and formulas for R chart
Methods and formulas for S chart
P chart
Methods and formulas for P chart
NP chart
Methods and formulas for NP chart
U chart
Methods and formulas for U chart
C chart
Methods and formulas for C chart
EXAMPLE
Copy the data.
1. Download the file.
Go to: https://support.minitab.com/en-us/datasets/control-charts-data-sets/camshaft-length-data/ and download CamshaftLength.MTW.
2. Open the data set with Minitab Statistical Software.
3. Select and Copy the data.
This example has 100 rows of data, so make sure to scroll down and get the complete data set.
Paste the data in the Minitab Connect platform.
1. Open the Navigation menu.
2. Select Tables from the menu.
3. Select Add New Table from the menu.
4. Enter the New Table information.
Complete the required fields (highlighted in our example) and any optional fields that you want to complete.
5. Select the File / Text / Template option.
6. Paste Data.
Notice that a Preview is generated after you paste data.
7. Save the data set.
Click the Save button.
Prepare the data.
1. Open the PREP tool.
2. Click Add All Field(s).
3. Click the Run button.
4. Select the SORT(S) tab.
Locate and select the Subgroup ID field in the option menu.
Ensure that the sort order of the data is in Ascending order based on the Subgroup ID column.
5. Click Run to apply your changes.
Chart the data.
1. Open the SPC tool.
2. Go to the SETUP tab.
3. Select a Control Chart.
For this example, select Xbar-R from the Control Chart menu.
4. Select a Plot.
For this example, select Machine 1 from the Plot menu.
5. Select the Subgroup Sizes.
For our example, select By Field from the Subgroup Sizes menu.
6. Select a Field.
For our example, select Subgroup ID from the Field menu.
7. Click Run to apply your changes.
8. Click the Save button.
Fill in the required fields (highlighted in our example). Add a Description if wanted (optional). Click SAVE.
Interpret the results.
Always look at the R chart first. If the R chart shows that the process variation is not in control, then the control limits on the Xbar chart are inaccurate.
The R chart shows that the process variation is in control for Machine 1. No points are out of control, and all the points fall within the control limits in a random pattern.
The Xbar chart shows that Machine 1 has one out-of-control point (1 point > K standard deviations from center line).
For more example data sets to use with control charts, go to:
https://support.minitab.com/datasets/