Question 1

What is the difference between worst-case and RSS tolerance stack-up?

Accepted Answer

Worst-case sums every tolerance arithmetically — it guarantees fit but is expensive. RSS (root-sum-square) assumes independent, normally-distributed parts whose extremes rarely coincide, giving a realistic spread for volume production. Monte Carlo samples the real distributions for non-normal or shifted cases.

Question 2

When should I use RSS instead of worst-case?

Accepted Answer

Use RSS for higher-volume production of many independent contributors; use worst-case for safety-critical fits, short chains, or low volume where any single bad assembly is unacceptable.

Question 3

How does Cpk relate to a stack-up?

Accepted Answer

Convert the predicted spread to Cpk against the limits: below ~1.33 you'll see rejects; above ~1.67 you may be paying for tolerance you don't need.

Tolerance Stackup Analyzer

Contribution to variation

Monte Carlo & Cpk