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

ABSTRACTData 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.KEYWORDS: Intelligent manufacturingtransfer learningconvolutional variational autoencoderthermoformingmodel explainability AcknowledgementsThe authors would like to thank colleagues’ support and helpful comments at the Composites Research Network (CRN) and the University of British Columbia, especially, Mr Kurt Yesilcimen for his assistance during the data collection phase. The authors would also like to sincerely recognize the contribution of their industrial collaborator, Hytec Kohler Canada and in particular Mr Diego Faiguenbaum.Disclosure statementNo potential conflict of interest was reported by the author(s).Supplemental dataSupplemental data for this article can be accessed online at https://doi.org/10.1080/0951192X.2023.2257623Additional informationFundingThis study was financially supported by the New Frontiers in Research Fund (NFRF) of Canada – Exploration stream (award number: NFRFE-2019-01440).