Smart manufacturing under limited and heterogeneous data: a sim-to-real transfer learning with convolutional variational autoencoder in thermoforming

Data in advanced manufacturing are often sparse and collected from various sensory devices in a heterogeneous and multi-modal fashion. Thus, for such intricate input spaces, learning robust and reliable predictive models for product quality assessments entails implementing complex nonlinear models s...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International journal of computer integrated manufacturing Ročník 37; číslo 1-2; s. 18 - 36
Hlavní autoři: Ramezankhani, Milad, Harandi, Mehrtash, Seethaler, Rudolf, Milani, Abbas S.
Médium: Journal Article
Jazyk:angličtina
Vydáno: Taylor & Francis 01.02.2024
Témata:
convolutional variational autoencoder
Intelligent manufacturing
model explainability
thermoforming
transfer learning
ISSN:0951-192X, 1362-3052
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Data in advanced manufacturing are often sparse and collected from various sensory devices in a heterogeneous and multi-modal fashion. Thus, for such intricate input spaces, learning robust and reliable predictive models for product quality assessments entails implementing complex nonlinear models such as deep learning. However, these 'data-greedy' models require massive datasets for training, and they tend to exhibit poor generalization performance otherwise. To address the data paucity and the data heterogeneity in smart manufacturing applications, this paper introduces a sim-to-real transfer-learning framework. Specifically, using a unified wide-and-deep learning approach, the model pre-processes structured sensory data (wide) as well as high-dimensional thermal images (deep) separately, and then passes the respective concatenated features to a regressor for predicting product quality metrics. Convolutional variational autoencoder (ConvVAE) is utilized to learn concise representations of thermal images in an unsupervised fashion. ConvVAE is trained via a sim-to-real transfer learning approach, backed by theory-based heat transfer simulations. The proposed metamodeling framework was evaluated in an industrial thermoforming process case study. The results suggested that ConvVAE outperforms conventional dimensionality reduction methods despite limited data. A model explainability analysis was conducted and the resulting SHAP values demonstrated the agreement between the model's predictions, theoretical expectations, and data correlation statistics.
ISSN:0951-192X
1362-3052
DOI:10.1080/0951192X.2023.2257623