Process Capability studies
Prepared by Rahul N Dalvi
Process capability
• Ability of the process to meet the design
specifications for a product or service.
• It makes sense if all the special or assignable
causes of variation have been eliminated and
the process is in a state of statistical control.
• It has three components Design
specifications, centering of the natural
variation , Range or spread of the variation.
4 possible outcomes of Natural
Variation v/s Specification.
• Specification > Natural variation
• Specification = Natural variation
• Specification < Natural variation
• Specification = Natural variation but both lies
on opposite sides.
Process capability studies
• A process capability study is a carefully
planned study designed to yield specific info.
about the performance of a process under
specified operating conditions.
• Also defined statistically as “ minimum spread
of a specific measurement variation which will
include 99.7% of measurements from the
given process” .
Process capability studies
• Where is the process centred?
• How much variability exists in the process ?
• Is the performance relative to the
specifications acceptable?
• What proportion of output will be expected to
meet specifications?
• What factors contribute to variability ?
Reasons for conducting a process
capability study
• Manufacturer may wish to determine a
performance baseline for a process.
• To prioritize projects for quality improvement.
• To provide statistical evidence of quality for
customers .
• To evaluate a new equipment by the
purchasing department.
Reasons for conducting a process
capability study
• To compare different suppliers by the
purchasing department.
• To evaluate new processes.
Types of process capability study
• Peak performance study how process
performs under ideal conditions.
• Process characterization study how process
performs under actual operating conditions
• Component variability study Determines
relative contribution of different sources of
total variation.
Process capability Ratio
• 6sigma = 6R
d2
• R = Range
• D2 constant depends on sample size
• Sigma = standard deviation
Process capability Ratio
• Cp = UTL-LTL
6sigma
• UTL = Upper tolerance Limit
• LTL = Lower Tolerance Limit
• Sigma= S.D. of the process.
• If Cp < 1.0 , it indicates a particular process is not
capable of consistently meeting design specifications.
• If Cp> 1.0, it indicates particular process is not capable
of consistently meeting design specifications.
Upper & lower capability indices
• If only one specification limit is given then
• CPU or Cpu = USL –u
3sigma
• LPU or Cpl = u-LSL
3 sigma
• Cpk = min {(USL –u)/3sigma , (u-LSL)/3 sigma }
• Cp process potential, Cpk actual capability of the
process.