A new statistical method for design and analyses of component tolerance

Abstract

Tolerancing conducted by design engineers to meet customers' needs is a prerequisite for producing highquality products. Engineers use handbooks to conduct tolerancing. While use of statistical methods for tolerancing is not something new, engineers often use known distributions, including the normal distribution. Yet, if the statistical distribution of the given variable is unknown, a new statistical method will be employed to design tolerance. In this paper, we use generalized lambda distribution for design and analyses component tolerance. We use percentile method (PM) to estimate the distribution parameters. The findings indicated that, when the distribution of the component data is unknown, the proposed method can be used to expedite the design of component tolerance. Moreover, in the case of assembled sets, more extensive tolerance for each component with the same target performance can be utilized.

A new method of rigid assemblies stochastic 3D tolerance analysis including thermal performance.

“…The same author also cites commercial software CETOL 6 Sigma as a powerful 3D tolerance analysis modeling tool that does not use MCM and solves for WC and statistical variation. Movahedi et al [2016] used a method named the percentile method (PM) to estimate statistical distribution parameters and the generalized lambda distribution for design and analysis of tolerances of the assembly components. According to the authors, the findings indicated that when the distribution of the component data is unknown, the proposed method could be used to accelerate the design of the tolerance of the component.…”