Enhanced classification of hydraulic testing of directional control valves with synthetic data generation

Production environments bring inherent system challenges that are reflected in the high-dimensional production data. The data is often nonstationary, is not available in sufficient size and quality, and is class imbalanced due to the predominance of good parts. Data-driven manufacturing analytics re...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Production engineering (Berlin, Germany) Ročník 17; číslo 5; s. 669 - 678
Hlavní autoři: Neunzig, Christian, Möllensiep, Dennis, Hartmann, Melanie, Kuhlenkötter, Bernd, Möller, Matthias, Schulz, Jürgen
Médium: Journal Article
Jazyk:angličtina
Vydáno: Berlin/Heidelberg Springer Berlin Heidelberg 01.10.2023
Springer Nature B.V
Témata:
Computer Assisted Approaches in Production Engineering
Directional control
Engineering
Generative adversarial networks
Industrial and Production Engineering
Industrial applications
Machine learning
Manufacturing
Mathematical analysis
Prediction models
Production
Synthetic data
Conditional tabular generative adversarial networks
Tabular variational autoencoder
Predictive quality
Semi-supervised learning
Quality control
Machine learning
ISSN:0944-6524, 1863-7353
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Production environments bring inherent system challenges that are reflected in the high-dimensional production data. The data is often nonstationary, is not available in sufficient size and quality, and is class imbalanced due to the predominance of good parts. Data-driven manufacturing analytics requires data of sufficient quantity and quality. In order to predict quality characteristics, production data is collected across processes in the industrial use case at Bosch Rexroth AG for the purpose of inferring results in hydraulic final inspection using machine learning methods. Since high quality data generation is costly, synthetic data generation methodologies offer a promising alternative to improve prediction models and thus generate safer, more accurate predictions for manufacturing companies. Among the synthetic data generation methodologies used, variational autoencoders compared to generative adversarial networks and synthetic minority oversampling technique methods are best suited to synthesize the feature with highest feature importance from a small sample data set compared to the production data and improve the prediction for the target variable.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0944-6524
1863-7353
DOI:10.1007/s11740-023-01204-8