Do you USE SPC CORRECTLY? Misapplication of statistical process control can damage your operations

摘要

To understand just how misleading data can be when viewed improperly, consider the data shown in these graphs. Using a histogram, you can see how the measurements stack up relative to the specification limits. By looking at the graph, what can you conclude about the process? Note that USL and LSI represent the upper and lower specification limits, respectively. While it's tempting to conclude that things are OK, and that the process is approximately centered between the specification limits, the answer to the question is "nothing." Because we have not viewed the data over time, we can't draw conclusions regarding the process. The data shown in the second graph illustrate exactly the same data as depicted in the histogram above. This second graph depicts the data collected over time. Viewing these data over time provides a more accurate description than the histogram. Here, the histogram misleads one to believe the information comes from a single distribution. This process has been shifting over time, however, so no single distribution actually describes the data. The distribution continues to change as time passes. If a product fails or a process performs inadequately, we attempt to discover what's wrong so we can fix it. That sounds reasonable enough. By reacting to the problem, however, we're allowing that process or product failure to control our behavior. Isn't it more effective to understand and control the process rather than allowing the process to control us?