𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Estimating gradients for statistical tolerance synthesis

✍ Scribed by Victor J Skowronski; Joshua U Turner

Publisher
Elsevier Science
Year
1996
Tongue
English
Weight
893 KB
Volume
28
Category
Article
ISSN
0010-4485

No coin nor oath required. For personal study only.

✦ Synopsis

Current statistical tolerance analyses calculate the distributions of critical dimensions or design functions for a given set of tolerances. However, the analyses cannot determine the effect of small changes in tolerance values without a complete reanalysis.

This inability to furnish gradient information restricts the use of optimization algorithms in tolerance synthesis to those which do not require gradients. This paper describes a technique for statistical tolerance analysis. In the technique, the continuous distribution of manufacturing variations is replaced by an equivalent discrete distribution. During the process of computing the discrete probabilities. gradient information is also computed. so that more efficient optimization algorithms can be used. Copyright ~"1 1996 Elsevier Science Ltd

πŸ“œ SIMILAR VOLUMES

Using Monte-Carlo variance reduction in
Using Monte-Carlo variance reduction in statistical tolerance synthesis
✍ Victor J Skowronski; Joshua U Turner πŸ“‚ Article πŸ“… 1997 πŸ› Elsevier Science 🌐 English βš– 768 KB

A statistical tolerance synthesis must analyse many sets of tolerances, each of which has a unique probability distribution. The Monte-Carlo technique that is typically used to evaluate the probability distribution must analyse large numbers of individual cases. The result is a huge number of indivi