Trustworthy and Generalizable Intelligent Diagnosis of Rotating Machinery under Complex Industrial Operating Conditions

Rotating machinery, including bearings, gearboxes, motors, pumps, compressors, turbines, and wind turbine drivetrains, plays a critical role in modern industrial and mechatronic systems. Intelligent fault diagnosis has achieved remarkable progress with the development of advanced sensing, signal processing, and artificial intelligence. However, many existing methods still rely on laboratory datasets collected under fixed operating conditions, while industrial equipment often operates under variable speed, variable load, strong noise, non-stationary signals, limited labels, and cross-machine data distribution shifts. These challenges significantly reduce the reliability, interpretability, and transferability of diagnostic models in practical applications. Therefore, developing trustworthy and generalizable intelligent diagnosis methods for rotating machinery under complex industrial operating conditions has become an urgent research topic.

This Research Topic aims to address the gap between high-performance diagnostic models in controlled experimental settings and reliable intelligent diagnosis in real industrial environments. The goal is to promote new theories, methods, and applications that improve the trustworthiness, robustness, and generalization capability of rotating machinery fault diagnosis. Particular attention will be given to diagnostic methods that can maintain stable performance under variable operating conditions, scarce fault samples, strong noise interference, and domain shifts across machines, working conditions, or industrial scenarios. Recent advances in physics-informed learning, explainable artificial intelligence, transfer learning, domain generalization, self-supervised learning, multimodal sensing, digital twins, and edge intelligence provide promising opportunities to overcome these challenges. This Research Topic seeks to bring together interdisciplinary contributions from mechanical engineering, mechatronics, artificial intelligence, condition monitoring, and prognostics and health management to support reliable, interpretable, and deployable intelligent diagnosis of rotating machinery.

This Research Topic welcomes Original Research, Review, Methods, Perspective, and industrial application studies related to trustworthy and generalizable intelligent diagnosis of rotating machinery. Potential topics include, but are not limited to:

(1) Robust fault diagnosis of rotating machinery under variable speed, variable load, strong noise, and non stationary operating conditions

(2) Cross condition, cross-domain, cross-machine, and cross scenario generalization for intelligent fault diagnosis

(3) Physics informed learning and mechanism-guided modeling for trustworthy rotating machinery diagnosis

(4) Explainable artificial intelligence and uncertainty quantification for diagnostic reliability assessment

(5) Self supervised learning, few shot learning, open set recognition, and unknown fault diagnosis

(6) Multisensor and multimodal data fusion using vibration, acoustic, current, temperature, pressure, or other industrial signals

(7) Digital twin enabled health monitoring, degradation modeling, and remaining useful life prediction

(8) Lightweight intelligent diagnostic models, edge intelligence, and real time deployment for industrial applications

(9) Predictive maintenance, health management, and decision making for rotating machinery mechatronic systems

(10) Industrial applications in bearings, gearboxes, motors, pumps, compressors, turbines, wind power systems, rail transit, aerospace, and smart manufacturing equipment

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
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• ... 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
• Hypothesis and Theory
• Methods
• Mini Review
• Opinion
• Original Research
• Perspective
• Review

Keywords: Rotating machinery; intelligent fault diagnosis; trustworthy AI; generalizable diagnosis; complex operating conditions; condition monitoring; predictive maintenance; explainable artificial intelligence; domain adaptation; industrial mechatronics

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.