Advanced
search

To read this content please select one of the options below:

Auto-encoder-based algorithm for the selection of key characteristics for products to reduce inspection efforts

Jonathan S. Greipel (Department of Model-based Systems, Chair of Production Metrology and Quality Management, WZL | RWTH Aachen University, Aachen, Germany)
Regina M. Frank (Department of Model-based Systems, Chair of Production Metrology and Quality Management, WZL | RWTH Aachen University, Aachen, Germany)
Meike Huber (Department of Model-based Systems, Chair of Production Metrology and Quality Management, WZL | RWTH Aachen University, Aachen, Germany)
Ansgar Steland (Institute of Statistics, RWTH Aachen University, Aachen, Germany)
Robert H. Schmitt (Department of Model-based Systems, Chair of Production Metrology and Quality Management, WZL | RWTH Aachen University, Aachen, Germany) (Fraunhofer Institute for Production Technology IPT, Aachen, Germany)

International Journal of Quality & Reliability Management

ISSN: 0265-671X

Article publication date: 8 December 2022

Issue publication date: 10 July 2023

153

Abstract

Purpose

To ensure product quality within a manufacturing process, inspection processes are indispensable. One task of inspection planning is the selection of inspection characteristics. For optimization of costs and benefits, key characteristics can be defined by which the product quality can be checked with sufficient accuracy. The manual selection of key characteristics requires substantial planning effort and becomes uneconomic if many product variants prevail. This paper, therefore, aims to show a method for the efficient determination of key characteristics.

Design/methodology/approach

The authors present a novel Algorithm for the Selection of Key Characteristics (ASKC) based on an auto-encoder and a risk analysis. Given historical measurement data and tolerances, the algorithm clusters characteristics with redundant information and selects key characteristics based on a risk assessment. The authors compare ASKC with the algorithm Principal Feature Analysis (PFA) using artificial and historical measurement data.

Findings

The authors find that ASKC delivers superior results than PFA. Findings show that the algorithms enable the cost-efficient selection of key characteristics while maintaining the informative value of the inspection concerning the quality.

Originality/value

This paper fills an identified gap for simplified inspection planning with the method for the efficient selection of key features via ASKC.

Keywords

Acknowledgements

Funding: The research that has led to the results presented in this paper has been conducted within the IGF project No. 20618 N/11 “App-basierte Aufwandsreduzierung bei der adaptiven Prüfung in der Produktion von Varianten” (App-based effort reduction in adaptive inspection planning in the production of variants, APProVe). The IGF project No. 20618 N/11 of the Forschungsgemeinschaft Qualität e.V. (FQS Research Association), August-Schanz-Straße 21A, 60433 Frankfurt am Main, Germany, was funded by the Federal Ministry for Economic Affairs and Climate Action via the AiF within the framework of the program for the promotion of the Industrial Collective Research (IGF) based on a resolution of the German Bundestag.

Citation

Greipel, J.S., Frank, R.M., Huber, M., Steland, A. and Schmitt, R.H. (2023), "Auto-encoder-based algorithm for the selection of key characteristics for products to reduce inspection efforts", International Journal of Quality & Reliability Management, Vol. 40 No. 7, pp. 1597-1620. https://doi.org/10.1108/IJQRM-11-2021-0408

Publisher

:

Emerald Publishing Limited

Copyright © 2022, Emerald Publishing Limited

Related articles

Manage cookies

We’re listening — tell us what you think

Join us on our journey