Six Sigma Tools – Measure Phase

Six Sigma Tools – Measure Phase

By Discovery Lean Six Sigma

0/5 stars (0 votes)

Six Sigma Tools – Measure Phase
 

This is the second post in our mini series exploring the tools used at each stage of a DMAIC project.  In the first post we looked at the define phase and so now we are ready to move onto the measure phase.

The main purpose of the measure phase in dmaic projects is to establish a baseline for the current process performance.

Once the existing level of variation is understood, the project team can analyse which inputs and process controls affect the output most significantly.  This allows them to more efficiently improve the process than if they had taken a trial and error approach.

One of the other measure phase deliverables is a measurement systems analysis.  This is critical to ensure the observed variation is not caused by the measurement equipment or operator.

Lets have a look at some of the tools used in the measure phase of dmaic.

Data Collection Plan

A data collection plan is used to manage the dmaic measure phase. It starts off by stating what needs to be measured, which is usually derived from Voice Of the Customer data gathered during the define phase.

The next step is to define ‘operational definitions’. These are understandable, unambiguous descriptions of what is to be measured or observed to ensure consistency (PANDE et al., 2000).

A simple example of the importance of tight operational definitions is asking a group to go and count how many cars they can see of a certain colour. Unless the colour is properly specified, it is highly likely that the observers will arrive at different results.

The next stage is to develop a data collection form.  It should be simple and easy to use to avoid mistakes occurring as it is completed. This requires stratification of data. For example, it might be necessary to measure how many customer returns are received. This would be a simple measurement. However, later on it might be necessary to break the number down to show where the returns were from or the reasons for their return. If this data is not collected in the first place then it creates problems later. Therefore an important aspect of the data collection plan is to predict what layers of data will be required.

Gauge Repeatability & Reproducibility (GR&R)

This is a test of the effectiveness of a measuring system and determines the proportion of variability contributed by the measurement system to the total variation. It involves repeating a measure in various environments to test against four criteria (PANDE et al., 2000):

  • Accuracy. How precise is the measurement?
  • Repeatability. If one person or piece of measuring equipment measures the sameitem more than once, will the same value be returned?
  • Reproducibility. If two or more people or machines measure the same thing, willthey get the same results?
  • Stability. Over time, will accuracy or repeatability deteriorate or shift?

One of the outputs of a GR&R study is the operator-part graph similar to that shown below. It is used to determine if there is a relationship between the operator taking the measurement and the part being measured. If the lines connecting the plotted points diverge significantly, indicating that operators are consistently measuring differently, then action needs to be taken.

Measure Phase

GR&R Operator-Part Graph

Check-sheet

A check-sheet can take many forms but is fundamentally a tool that aids a person to capture data. Some common types of check-sheets include the following (PANDE et al., 2000):

  • Defect or Cause Check-sheet. Used to record types of defects or causes of defects.
  • Data Sheet. Captures readings, measures or counts quantities.
  • Frequency Plot Check-sheet. Records a characteristic of an item along a counted scale or continuum.
  • Concentration Diagram Check-sheet. Features a picture of the item or document being observed; data collectors then mark where problems, defects or damage are seen on the item.
  • Traveller Check-sheet. A ‘traveller’ is any kind of check-sheet that ‘moves’ with the product or service through the process. Data about that item is then recorded in an appropriate place on the form.

The advantages of using check sheets include (GEORGE et al., 2005):

  • Faster capture and compilation of data.
  • Consistent data from different people.
  • Captures essential stratification factors that might otherwise be overlooked.

Control Charts

Control charts are easy-to-use charts which display graphically both special and common cause variation in a process. They are sometimes called Shewhart charts, after their inventor, Walter Shewhart. A control chart consists of a centerline, typically the mean, as well as upper and occasionally lower control limits. The data is then plotted over a period of time. An example of a control chart is displayed:

Control Chart

Control Chart

It is possible to use control charts to identify special cause variation using several ‘rules of thumb’:

  • 1 data point falling outside the control limits indicates a shift in the mean, an increase in the standard deviation, or a single aberration in the process.
  • 6 or more points in a row steadily increasing or decreasing indicates a drift in the process mean (or standard deviation if they only increase).
  • 9 or more points in a row on one side of the centerline indicates a shift in the process mean or standard deviation.
  • 14 or more points alternating up and down indicates systematic effects, such as two alternately used machines, vendors or operators.

(GEORGE et al., 2005)

Summary

The lean six sigma measure phase is the second step after the define stage.  During the six sigma measure phase tools such as control charts, check sheets, Gage R&R and data collection plans are used.

One of the most important deliverables of the measure phase is a measurement systems analysis.  This is to ensure that the variation being measured in the process is indeed caused by the process and not variation in the measurement process itself.

Once the six sigma dmaic measure phase is complete, it is time to move into the analyse phase.

To find out more about six sigma tools, check out the other phases in this mini series:
 

The post Six Sigma Tools – Measure Phase appeared first on Lean Process.





Original: http://www.leanprocess.net/six-sigma-tools-measure-phase/
By: Lean Process
Posted: November 25, 2013, 1:00 pm

comments powered by Disqus

Discovery Lean Six Sigma

Dummy user for scooping articles

I'm a dummy user created for scooping  great articles in the network for the community.