Process Capability

Process capability quantifies the relationship between the natural variation of a process and the specification limits it must meet. The Cp index compares the tolerance width to the process spread (6 standard deviations): Cp = (USL - LSL) / 6σ. A Cp of 1.0 means the process spread exactly equals the tolerance, while Cp of 2.0 means the tolerance is twice as wide as the process spread. The Cpk index additionally accounts for how well the process is centered within the tolerance: Cpk = min[(USL - mean) / 3σ, (mean - LSL) / 3σ].

Common capability targets are Cpk ≥ 1.33 (equivalent to a 4-sigma process) for established processes and Cpk ≥ 1.67 (5-sigma) for new processes or safety-critical applications. A capable process (high Cpk) produces very few defects, while an incapable process (low Cpk) requires inspection, sorting, or process changes to meet quality requirements.

For calibration management, process capability analysis depends directly on measurement system quality. The observed process variation includes both the true process variation and the measurement system variation. If the measurement system contributes significant variation (as revealed by Gage R&R), the calculated process capability may be understated. This is why MSA should precede process capability studies — you need to know your measurement system is adequate before drawing conclusions about the process. Furthermore, the measurement instrument's calibration tolerance must be appropriate for the process tolerance being evaluated, following the TUR guidelines.