*** Call for Papers ***

A Special Issue for the journal Applied Sciences (SCIE Q1, CiteScore 5.5).

Guest Editors:

Dr. Alexandru Stanciu, National Institute for Research and Development in Informatics - ICI Bucharest, Romania

Dr. Rui Araújo, Institute of Systems and Robotics (ISR-UC), Department of Electrical and Computer Engineering (DEEC-UC), University of Coimbra, Portugal

Special Issue Information:

Advances in artificial intelligence are driving a paradigm shift in machinery health monitoring, enabling proactive maintenance and increased operational efficiency across diverse industries. By harnessing real-time sensor data, machine learning techniques, and cutting-edge technologies such as digital twins, AI-based monitoring systems can detect early signs of degradation, accurately diagnose faults, and predict failures before they lead to costly downtime. This holistic approach—combining intelligent data analytics at the cloud and edge, sophisticated anomaly detection methods, and new forms of human–machine collaboration—represents a transformative leap from traditional time-based maintenance toward truly predictive and prescriptive strategies.

This Special Issue seeks original research articles, case studies, and review papers covering the latest advancements and future trends in AI-based machinery health monitoring.

Potential topics include, but are not limited to:

- Machine learning, deep learning, and hybrid techniques for fault diagnosis and prognostics.
- Large Language Models (LLMs), agenting workflows and frameworks for anomaly detection, predictive maintenance, and intelligent fault diagnosis.
- Advanced sensing technologies, Internet of Things (IoT) integration, and edge/cloud architectures.
- Digital twin development for real-time monitoring and “what-if” simulations.
- Remaining useful life (RUL) estimation and performance optimization.
- Applications of augmented/virtual reality in maintenance tasks.
- Industry 4.0/5.0 concepts and sustainable, energy-efficient maintenance solutions.

Submission Guidelines:

Manuscripts must be original, high-quality contributions that have not been previously published or are not under consideration elsewhere. Extended versions of conference papers are welcome, provided they demonstrate significant new content and clear improvements over the original work. All submitted papers will undergo a rigorous peer-review process.

For full details and to submit your manuscript, please visit the Special Issue website:

https://www.mdpi.com/journal/applsci/special_issues/B0773RBQ33

Submission Deadline:
30 December 2025