Maximizing model generalization for machine condition monitoring with Self-Supervised Learning and Federated Learning

Matthew Russell, Peng Wang

Research output: Contribution to journalArticlepeer-review


Deep Learning (DL) can diagnose faults and assess machine health from raw condition monitoring data without manually designed statistical features. However, practical manufacturing applications require robust and repeatable solutions that can be trusted in dynamic environments. Machine data is often unlabeled and from very few health conditions (e.g., only normal operating data). Furthermore, models often encounter shifts in domain as process parameters change and new categories of faults emerge. Traditional supervised learning may struggle to learn compact, discriminative representations that generalize to these unseen target domains since it depends on having plentiful classes to partition the feature space with decision boundaries. Transfer Learning (TL) with domain adaptation attempts to adapt these models to unlabeled target domains but assumes similar underlying structure that may not be present if new faults emerge. This study proposes focusing on maximizing the feature generality on the source domain and applying TL via weight transfer to copy the model to the target domain. Specifically, Self-Supervised Learning (SSL) with Barlow Twins may produce more discriminative features for monitoring health condition than supervised learning by focusing on semantic properties of the data. Furthermore, Federated Learning (FL) for distributed training may also improve generalization by efficiently expanding the effective size and diversity of training data by sharing information across multiple client machines. Results show that Barlow Twins outperforms supervised learning in an unlabeled target domain with emerging motor faults when the source training data contains very few distinct categories. Incorporating FL may also provide a slight advantage by diffusing knowledge of health conditions between machines. Future work should continue investigating SSL and FL performance in these realistic manufacturing scenarios.

Original languageEnglish
Pages (from-to)274-285
Number of pages12
JournalJournal of Manufacturing Systems
StatePublished - Dec 2023

Bibliographical note

Publisher Copyright:
© 2023 The Society of Manufacturing Engineers


  • Condition monitoring
  • Emerging faults
  • Fault diagnosis
  • Federated learning
  • Self-supervised learning
  • Transfer learning

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Hardware and Architecture
  • Industrial and Manufacturing Engineering


Dive into the research topics of 'Maximizing model generalization for machine condition monitoring with Self-Supervised Learning and Federated Learning'. Together they form a unique fingerprint.

Cite this