Automate Quality Prediction in an End-of-Line Test of a Highly Variant Production of Geared Motors – Discussion of a Full Concept

##plugins.themes.bootstrap3.article.main##

##plugins.themes.bootstrap3.article.sidebar##

Published Jun 29, 2021
Peter Wissbrock David Pelkmann Björn Tölle

Abstract

In the production of complex and modular mechanical components such as geared motors the diversity of variants is rising continuously. At the same time the requirement for good sound quality of the product is increasing. In a batch-size-one production it is hard for the assembly operator to determine the product quality consistent. Automation of the end-of-line test leads to several problems. Classical vibration and sound measurements take a lot of time and the features have to be defined individually for every single product configuration. This paper presents a full concept for automation or semi-automation of the end-of-line test in a highly variant production of geared motors. It is shown how acoustic measurement can be done in a common industrial production and gives an overview of typically used machine learning methods and their features for quality prediction of geared motors. Further a concept for dealing with the lack of labeled examples is addressed to analyze historically unknown product configurations. Finally it is discussed how to structure classifiers to capture of all known and unknown faults. The end-of-line concept is a basic module for industry 4.0 and can be generalized to all modern industrial productions where batch-size-one and a high diversity of variants are typical.

How to Cite

Wissbrock, P., Pelkmann, D., & Tölle, B. (2021). Automate Quality Prediction in an End-of-Line Test of a Highly Variant Production of Geared Motors – Discussion of a Full Concept. PHM Society European Conference, 6(1), 10. https://doi.org/10.36001/phme.2021.v6i1.2803
Abstract 53 | PDF Downloads 61

##plugins.themes.bootstrap3.article.details##

Keywords

quality prediction, end-of-line, highly variant production, geared motors, diversity of variants, product quality, acoustic monitoring, industry 4.0, fault classification, failure detection, domain adaptation

Section
Technical Papers