Generating Manufacturing Distributions for Sampling-based Tolerance Analysis using Deep Learning Models

Schächtl P, Roth M, Bräu J, Götz S, Schleich B, Wartzack S (2024)

Publication Type: Journal article

Publication year: 2024

Journal

Procedia CIRP Curran

Book Volume: 129

Pages Range: 103-108

DOI: 10.1016/j.procir.2024.10.019

Abstract

Sampling-based tolerance analysis is a powerful tool for evaluating the quality of functional products, but requires realistic manufacturing distributions. However, the determination of resulting manufacturing distributions is usually associated with a high financial and time expenditure, especially for novel technologies such as Additive Manufacturing. Usually, sampling techniques are used to reproduce the original distribution of manufacturing variations based on statistical moments. In most cases, simplifying assumptions are made for this purpose, potentially leading to an inadequate representation of the correlation between machine and process parameters in the resulting distribution. In the worst case, this can lead to a falsification of the tolerance analysis results. Aiming to address this challenge, this paper presents an approach to imitate real-world manufacturing distributions using generative Machine Learning techniques based on Deep Learning with small real data sets. This enables a realistic reproduction of quasi-real manufacturing distributions and omits conventional sampling techniques. The general procedure and its applicability are shown via illustrative use cases from the tolerancing domain.

Authors with CRIS profile

Paul Schächtl Chair of Engineering Design (KTmfk) Martin Roth Chair of Engineering Design (KTmfk) Stefan Götz Chair of Engineering Design (KTmfk) Benjamin Schleich
Sandro Wartzack Chair of Engineering Design (KTmfk)

Related research project(s)

None - None None - None None - None

Involved external institutions

Technische Universität Darmstadt DE Germany (DE)

How to cite

APA:

Schächtl, P., Roth, M., Bräu, J., Götz, S., Schleich, B., & Wartzack, S. (2024). Generating Manufacturing Distributions for Sampling-based Tolerance Analysis using Deep Learning Models. Procedia CIRP, 129, 103-108. https://doi.org/10.1016/j.procir.2024.10.019

MLA:

Schächtl, Paul, et al. "Generating Manufacturing Distributions for Sampling-based Tolerance Analysis using Deep Learning Models." Procedia CIRP 129 (2024): 103-108.

BibTeX: Download