Simon Dahdal, Lorenzo Colombi, Matteo Brina, Alessandro Gilli, Mauro Tortonesi, Massimiliano Vignoli, and Cesare Stefanelli

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

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. Reference:

DOI: 10.36244/ICJ.2024.2.1

Download 

Please cite this paper the following way:

Simon Dahdal, Lorenzo Colombi, Matteo Brina, Alessandro Gilli, Mauro Tortonesi, Massimiliano Vignoli, and Cesare Stefanelli, "An MLOps Framework for GAN-based Fault Detection in Bonfiglioli’s EVO Plant ", Infocommunications Journal, Vol. XVI, No 2, June 2024, pp. 2-10., https://doi.org/10.36244/ICJ.2024.2.1