An adaptive machine learning methodology to determine manufacturing process parameters for each part

Research output: Contribution to journalConference articlepeer-review

Abstract

The identification of appropriate manufacturing process parameters typically relies on rule-based schemes, expertise, and domain knowledge of highly skilled workers. Usually, the parameter settings remain the same for each part in an individual production lot once an acceptable quality is reached. Each part, however, has slightly different properties and part-specific parameter settings have the opportunity to increase quality and reduce scrap. We propose a simple linear regression model to identify process parameters based on experimental data and extend that model with ideas from time series analysis to achieve highly-accurate, part-specific parameter settings in a real-world manufacturing use case. We show the usefulness of exploiting the (autocorrelated) structure of regression residuals to improve the predictive performance of regression models in manufacturing environments.

Original languageEnglish
Pages (from-to)764-771
Number of pages8
JournalProcedia Computer Science
Volume180
DOIs
Publication statusPublished - 2021
Event2nd International Conference on Industry 4.0 and Smart Manufacturing, ISM 2020 - Virtual, Online, Austria
Duration: 23 Nov 202025 Nov 2020

Keywords

  • adaptation
  • autocorrelation
  • concept drift
  • industry 4.0
  • machine learning
  • manufacturing
  • parameter optimization
  • process optimization
  • process parameters
  • regression analysis

Fingerprint

Dive into the research topics of 'An adaptive machine learning methodology to determine manufacturing process parameters for each part'. Together they form a unique fingerprint.

Cite this