How to Interpret Shewhart Control Chart Patterns

Now that we studied a little bit about control charts, it is also important to know how to interpret them. The first thing we must have in mind is about the control charts zones. Look at the picture below.

After that, we have some tests to do, that will help in the interpretation of the control charts. Those are:

•Test 1: Extreme Points
•Test 2: Two out of three points in Zone A or Beyond
•Test 3: Four out of five points in Zone B or Beyond
•Test 4: Runs above or below the center line
•Test 5: Linear Trend Identification
•Test 6: Oscillatory Trend Identification
•Test 7: Avoidance of Zone C
•Test 8: Run in Zone C

 

Test 1: Extreme Points:

•Points beyond the control limits—The existence of a single point beyond a control limit signals the presence of an out-of-control condition.
 
•Find the cause(s) and take corrective action.

 

Test 2: Two out of three points in Zone A or Beyond

•Applies only to $ \overline{X} $ chart. The existence of two of any three successive points in zone A or beyond signals the presence of an out-of-control condition.
 
•Find cause(s) and take corrective action

 

Test 3: Four out of Five points in Zone B or Beyond

•Applies only to $ \overline{X} $ chart. Four out of five successive points in Zone B or beyond signals the presence of an out-of-control condition. This may help to detect smaller shifts in the process mean which do not give rise to extreme points.
 
•Find the cause(s) and take corrective action.

 

Test 4: Runs Above or Below the Centerline

•Applies to both $ \overline{X} $  and $ R $ charts.
 
•Long runs (eight or more successive points) either strictly above or below the centerline indicates strong evidence that the process mean or variability has shifted from the centerline.
 
•Find the cause(s) and take corrective action

 

Test 5: Linear Trend Identification

•When six successive points on either $ \overline{X} $ or the $R$ chart show continuing increase or decrease, a systematic trend in the process is signaled.
 
•Neither the zones nor the centerline comes into play for this test.
 
•Find the cause(s) and take corrective action.

 

Test 6: Oscillatory Trend Identification

•When 14 successive points oscillate up ad down on either the $ \overline{X} $ or the $R$ chart, a systematic trend in the process is signaled.
 
•Neither the chart centerline nor the zones come into play for this test.
 
•Find cause(s) and take corrective action

 

Test 7: Avoidance of Zone C

•When 8 successive points occurring on either side of the centerline avoid zone C (no points in Zone C), an out of control condition is signaled.
 
•This rule applies only to $ \overline{X} $ chart.
 
•This could be due to over control of the process or more than one process being charted on the same chart.
 
• Find cause(s) and take corrective action

 

Test 8: Run in Zone C

•When 15 successive points on the $ \overline{X} $ chart fall only in Zone C, to either side of the centerline, an out-of-control condition is signaled.
 
•This could result from a decrease in process variability that has not been properly accounted for in the $ \overline{X} $ chart.
 
•Recalculate the mean and the UCL and LCL. 

 

It is also important to know some useful generic conditions:

–Trends/Cyclic behavior: Systematic changes in process environment, worker fatigue, maintenance schedules, tool wear conditions, accumulation of waste material, and contamination
–High Proportion of Points Near or Beyond Control Limits: Over control of the process, large differences in incoming raw materials, charting more than one process on the single chart
–Sudden shifts in levels: New machine/die/tooling, a new worker, a new batch of raw material, change in the measurement system, change in the production method.