Conference Topics
The conference welcomes original contributions addressing theoretical developments, methodological advances, and industrial applications related to predictive maintenance and Prognostics and Health Management (PHM). Particular attention will be given to approaches that integrate data-driven techniques, advanced diagnostics and prognostics, and intelligent decision-support tools to enhance the reliability, availability, and sustainability of industrial systems.
Authors are invited to submit original research papers addressing the following topics:
Data and Signal Processing
This topic focuses on methods for acquiring, processing, and analyzing industrial data and sensor signals to support predictive maintenance. Contributions may address signal filtering, feature extraction, data fusion, and data-driven modeling techniques. Particular emphasis is placed on artificial intelligence and machine learning methods capable of transforming raw operational data into meaningful information for monitoring and understanding the behaviour of industrial systems.
Fault Detection and Diagnostics
This topic addresses approaches for detecting anomalies and diagnosing faults in industrial equipment and processes. Contributions may include model-based, data-driven, or hybrid diagnostic methods, condition monitoring techniques, and pattern recognition algorithms. The objective is to enable early fault detection and accurate identification of failure causes in order to improve system reliability, safety, and operational continuity.
Prognostics (Remaining Useful Life)
This topic focuses on methods for predicting the future health condition of components and estimating their Remaining Useful Life (RUL). Contributions may include degradation modeling, prognostic algorithms, hybrid prognostic approaches, and uncertainty management techniques. These approaches support proactive maintenance planning and help reduce unexpected failures and operational downtime.
Decision-Support
This topic focuses on tools and methodologies that support maintenance decision-making both for diagnostic and prognostic purposes and based on diagnostic and prognostic information within Predictive Maintenance (PdM) and Prognostics and Health Management (PHM) frameworks. Contributions may address approaches that assist in fault identification, health state assessment, degradation analysis, and Remaining Useful Life (RUL) prediction, as well as methods that leverage diagnostic and prognostic results to guide maintenance planning and operational decisions.
