Mariela Cerrada
Papers
1
Total Citations
22
H-Index
1
About
Mariela Cerrada is a leading researcher in intelligent fault diagnosis and predictive maintenance for industrial robotic systems. Her work focuses on overcoming critical data challenges in machine learning-based fault detection, particularly the scarcity of labeled fault condition data. In her highly cited 2020 study, she pioneered the use of Generative Adversarial Networks (GANs) as an oversampling method to generate synthetic fault data, enabling more robust training of diagnostic models for industrial robotic manipulators. This contribution directly addresses a major bottleneck in real-world maintenance applications, where collecting sufficient failure data is often impractical or dangerous. With over 22 citations on this work alone, Cerrada’s research has significantly advanced the reliability and safety of automated manufacturing systems. Her broader contributions span signal processing, feature extraction, and data-driven condition monitoring, making her a key figure in bridging the gap between deep learning and industrial engineering. Students and researchers in prognostics and health management (PHM) will find her work essential for understanding how generative models can transform sparse, imbalanced datasets into actionable diagnostic tools.
Research Focus
Key Achievements
Top Papers
- 1