Machine Learning (ML) plays a crucial role in Industry 4.0, enabling predictive fault detection (FD) by analyzing vast amounts of log data. However, current ML approaches often rely on single-task learning, neglecting the diverse nature of log data and the prediction of interrelated faults. Moreover, multi-view learning (MVL) and multi-task learning (MTL) are usually applied disjointly without applying joint learning across tasks and views. To address these gaps, we a novel approach which leverages multi-task and multi-view learning frameworks, augmented by a multi-label Cross Entropy loss (MTMVL-CE). MTMVL-CE improves generalization performance between and within different fault types, enabling the classification of multiple faults in complex industrial machines. Indeed, MTMVL-CE optimizes classification performance by learning across numerous faults simultaneously, achieving an accurate representation of heterogeneous log data, robust fault classification, and feasible generalization over time. We tested our approach through extensive experiments on an real use case involving FD in a complex banknote recirculator device inside Automated Teller Machines. Our results demonstrate MTMVL-CE’s superior performance compared to MTL and MVL competitors in capturing fault interdependencies and providing accurate, reliable predictions. • MTMVL-CE: unified framework for multi-source industrial fault detection. • Jointly optimizes within-task and between-task fault dependencies. • Correlation-based regularizer models task relationships. • Validated on 7400 heterogeneous real-world ATM log records. • Superior temporal generalization compared to state-of-the-art approaches.
Rosati et al. (Wed,) studied this question.