English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Process monitoring and control are essential in modern industries forensuring high quality standards and optimizing production performance. Thesetechnologies have a long history of application in production and have hadnumerous positive impacts, but also hold great potential when integrated withIndustry 4.0 and advanced machine learning, particularly deep learning,solutions. However, in order to implement these solutions in production andenable widespread adoption, the scalability and transferability of deeplearning methods have become a focus of research. While transfer learning hasproven successful in many cases, particularly with computer vision andhomogenous data inputs, it can be challenging to apply to heterogeneous data.Motivated by the need to transfer and standardize established processes todifferent, non-identical environments and by the challenge of adapting toheterogeneous data representations, this work introduces the Domain AdaptationNeural Network with Cyclic Supervision (DBACS) approach. DBACS addresses theissue of model generalization through domain adaptation, specifically forheterogeneous data, and enables the transfer and scalability of deeplearning-based statistical control methods in a general manner. Additionally,the cyclic interactions between the different parts of the model enable DBACSto not only adapt to the domains, but also match them. To the best of ourknowledge, DBACS is the first deep learning approach to combine adaptation andmatching for heterogeneous data settings. For comparison, this work alsoincludes subspace alignment and a multi-view learning that deals withheterogeneous representations by mapping data into correlated latent featurespaces. Finally, DBACS with its ability to adapt and match, is applied to avirtual metrology use case for an etching process run on different machinetypes in semiconductor manufacturing.

Heterogeneous Domain Adaptation and Equipment Matching: DANN-based Alignment with Cyclic Supervision (DBACS)