Advances in Condition Monitoring and Fault Diagnosis of Rotating Machinery: Model-based, Signal-based and Data-driven Perspectives

Rotating machinery, including turbines, compressors, pumps, engines, and industrial drives, is central to modern energy and manufacturing infrastructure. Unforeseen faults lead to costly downtime and safety hazards, so condition-based maintenance depends on the timely detection of incipient defects. During the past three decades, the discipline has progressed from classical vibration analysis to sophisticated analytical and computational frameworks that capture nonlinear, non-stationary dynamics. Physics-based modeling, high-resolution signal processing, and artificial-intelligence techniques now coexist, each contributing complementary insight into machine health. A comprehensive perspective that synthesizes these methodologies is essential for achieving high diagnostic accuracy across diverse machines, loading conditions, and life-cycle stages.

Although significant progress has been achieved, three persistent obstacles continue to constrain robust diagnostics: first, model uncertainty under variable operating regimes and environmental disturbances; second, the scarcity or imbalance of labeled fault data, particularly for rare failure modes; and third, the computational burden associated with real-time deployment on embedded or edge platforms. This special issue will collect state-of-the-art contributions that integrate model-based and data-driven perspectives to deliver accurate, interpretable, and scalable fault-diagnosis frameworks for rotating machinery. We welcome studies that refine analytical and observer-based methods through adaptive parameters, nonlinear dynamics, or reduced-order modeling; that advance high-resolution signal analysis for weak-fault detection; that exploit machine learning, deep learning, transfer learning, or physics-informed networks to extract latent health indicators; and that incorporate prognosis, uncertainty quantification, and digital-twin constructs to support maintenance decisions.

Submissions may address theory, algorithms, and industrial practice for all categories of rotating equipment, including turbomachinery, drivetrains, bearings, gears, shafts, and electromechanical assemblies. Acceptable manuscript types are original research, systematic reviews, data-descriptor papers, and validated case studies. Topics of interest include:

• Analytical and observer-based fault isolation;
• Parameter estimation and Kalman or particle filtering;
• Advanced signal processing such as wavelets, empirical-mode decomposition, and sparse representation;
• Machine- or deep-learning pipelines for classification, regression, and remaining-useful-life prediction;
• Domain adaptation, self-supervision, and small-sample learning;
• Physics-informed digital twins and hybrid models;
• Multi-sensor data fusion, edge or cloud deployment, and real-time health indicators;
• Benchmarking datasets, open-source tools, and interpretable diagnostics;
• Contributions should demonstrate methodological novelty, rigorous validation, and clear relevance to predictive maintenance practice.

Article types and fees

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• ... View all formats

Articles that are accepted for publication by our external editors following rigorous peer review incur a publishing fee charged to Authors, institutions, or funders.

Article types

This Research Topic accepts the following article types, unless otherwise specified in the Research Topic description:

• Brief Research Report
• Editorial
• FAIR² Data
• FAIR² DATA Direct Submission
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review

Keywords: Rotating machinery; Condition monitoring; Fault diagnosis; Model-based methods; Signal processing; Machine learning; Deep learning; Digital twin; Prognostics; Data fusion

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.