In the context of Industry 4.0, the importance of prognostics and predictive maintenance cannot be overstated. The ability to predict equipment undesired events (faults or failures) and identify potential issues before they occur has become crucial in today's industry, as it can save companies time and money while enhancing safety and reliability. Furthermore, prognostics and predictive maintenance are playing an increasingly essential role in complex systems, where maintenance tasks are planned based on anomaly detection, fault diagnosis, and prognostics.
The aim of this special issue is to highlight the advancements in prognostics and predictive maintenance for complex manufacturing systems, particularly those that require multi-scale analysis, heterogeneous sources of data, and complex decision-making under constraints. The contributions should address the challenges posed by predictive maintenance in Industry 4.0, including incomplete physics knowledge, uncertainties in predictions, and issues related to the quality and relevance of data. Both experimental and theoretical works are welcome, including critical reviews and surveys of the state of the art and practice in Prognostics and health Management (PHM) and predictive maintenance as well as their applications across various industry sectors.
The topics of interest for this special issue include, but are not limited to:
- Advanced prognostics approaches
- Fault detection, diagnostics, and prognostics,
- Degradation modelling
- Reliability assessment and risk management
- Construction of health indicators,
- Feature engineering for PHM,
- Signal processing, image processing, and natural language processing for PHM,
- Data mining and big data in PHM,
- Machine Learning for PHM,
- Condition-based maintenance,
- Predictive maintenance,
- Maintenance optimization.
Reinforcement Learning for maintenance decision-making
