A generative neural network model for the quality prediction of work in progress products
View / Open Files
Publication Date
2019-12-01Journal Title
Applied Soft Computing Journal
ISSN
1568-4946
Volume
85
Language
English
Type
Article
This Version
AM
Metadata
Show full item recordCitation
Wang, G., Ledwoch, A., Hasani, R., Grosu, R., & Brintrup, A. (2019). A generative neural network model for the quality prediction of work in progress products. Applied Soft Computing Journal, 85 https://doi.org/10.1016/j.asoc.2019.105683
Abstract
© 2019 Elsevier B.V. One of the key challenges in manufacturing processes is improving the accuracy of quality monitoring and prediction. This paper proposes a generative neural network model for automatically predicting work-in-progress product quality. Our approach combines an unsupervised feature-extraction step with a supervised learning method. An autoencoding neural network is trained using raw manufacturing process data to extract rich information from production line recordings. Then, the extracted features are reformed as time-series and are fed into a multi-layer perceptron for predicting product quality. Finally, the outputs are decoded into a forecast quality measure. We evaluate the performance of the generative model on a case study from a powder metallurgy process. Our experimental results suggest that our method can precisely capture the defective products.
Identifiers
External DOI: https://doi.org/10.1016/j.asoc.2019.105683
This record's URL: https://www.repository.cam.ac.uk/handle/1810/297284
Rights
All rights reserved, Attribution-NonCommercial-NoDerivatives 4.0 International
Licence URL: http://creativecommons.org/licenses/by-nc-nd/4.0/
Recommended or similar items
The following licence files are associated with this item: