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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.