An MLOps Framework for GAN-based Fault Detection in Bonfiglioli’s EVO Plant

Dahdal, Simon and Colombi, Lorenzo and Brina, Matteo and Gilli, Alessandro and Tortonesi, Mauro and Vignoli, Massimiliano and Stefanelli, Cesare (2024) An MLOps Framework for GAN-based Fault Detection in Bonfiglioli’s EVO Plant. INFOCOMMUNICATIONS JOURNAL, 16 (2). pp. 2-10. ISSN 20612079

Preview

Text InfocomJournal_1.pdf - Published Version Download (1MB) | Preview

Abstract

In Industry 5.0, the scarcity of data on defective components in smart manufacturing leads to imbalanced data sets. This imbalance poses a significant challenge to the develop ment of robust Machine Learning (ML) models, which typically require a rich variety of data for effective training. The imbal ance not only restricts the models’ accuracy but also their ap plicability in diverse industrial scenarios. To tackle this issue, our research delves into the capabilities of Deep Generative Models, with a special focus on Generative Adversarial Networks, for the generation of synthetic data. This approach is aimed at rectify ing dataset imbalances, thereby enhancing the training process of ML models. We demonstrate how synthetic data can substan tially bolster the performance and reliability of ML models in industrial settings. Furthermore, the paper presents an innova tive MLOps pipeline and architecture, meticulously designed to incorporate Deep Generative Models (DGMs) into the entire ML development cycle. This solution is automated and goes beyond mere automation; it is self-optimizing and capable of making necessary corrections, specifically engineered to address the dual challenges of data imbalance and scarcity, thus enabling more precise and dependable ML applications in smart manufacturing.

Actions (login required)

Edit Item