Process control

From HMCwiki

Statistical process control is a methodology using statistical techniques to measure and analyze the variation in a process.

Control Chart: A moving picture of the variation in a process. A control chart will help discover how much variability in a process is due to common cause variation and how much is due to special cause variation. A control chart consists of a run chart together with an upper control limit (UCL), a lower control limit (LCL), and a central line (CL).

Common Cause Variation: Natural, inevitable, inherent system variation.

Special Cause Variation: Comes from sources outside the system. When data points fall outside the upper or lower control limits in a control chart, they are considered to be special causes.

Stable Process: Control chart exhibits only common cause variation. There are no data points outside the upper or lower control limits in a control chart. This process is said to be in statistical control.

Variables Data: Involves the measurement of units. Each measure is expressed as a number on a continuous scale of measurement, where a fractional or partial unit is possible (i.e., time).

Attributes Data: Involves counting of events, items, or units based on given criteria. Data are expressed as whole numbers on a discrete scale of measurement or as portions or percent of a larger set.

Central Line (CL): Represents the average of the process data.

Upper Control Limit (UCL): Limit calculated from data that sets an upper boundary in separating special cause variation from common cause variation. The upper control limit is three standard deviations (+3σ) above the central line.

Lower Control Limit (LCL): Limit calculated from data that sets a lower boundary in separating special cause variation from common cause variation. The lower control limit is three standard deviations (-3σ) below the central line.

How to read a control chart*

Determine if the process mean (central line) is where it should be relative to specifications, needs, or objectives. Analyze the data relative to the control limits; distinguishing between common and special causes. If a special cause is identified, it must be eliminated before the control chart can be used as a monitoring tool. The process is in “statistical control” when it is not being affected by special causes. All the points must fall within the control limits and they must be randomly dispersed about the central line for it to qualify as “in-control”. NOTE: Control does not necessarily mean that the product or service will meet your needs. It only means that the process is consistent.

Brassard, M., & Ritter, D. (1994). The Memory Jogger II. GOAL/QPC.

*Assumes that control limits and central line calculated from data with no special causes.

Questions to ask when investigating an “out of control” process

1. Are there differences in the measurement accuracy of instruments / methods used?
2. Are there differences in the methods used by different personnel?
3. Is the process affected by the environment, e.g., temperature, humidity?
4. Has there been a significant change in the environment?
5. Is the process affected by predictable conditions? Example: tool wear
6. Were any untrained personnel involved in the process at the time?
7. Has there been a change in the source for input to the process? Example: raw materials, information
8. Is the process affected by employee fatigue?
9. Has there been a change in policies or procedures?
10. Is the process adjusted frequently?
11. Did the samples come from different parts of the process? Shifts? Individuals?
12. Are employees afraid to report “bad news”?

Brassard, M., & Ritter, D. (1994). The Memory Jogger II. GOAL/QPC\

If you would like to provide feedback or discuss the content of this article, please visit the discussion page. To be automatically notified by email of any changes or additions to the article or discussions about this article, please click here.