This study proposes an explainable domain adaptation neural network (EDANN) to address the critical data scarcity and “black-box” limitations in artificial intelligence (AI) driven rotor fault diagnosis. In practical rotor monitoring systems, real fault samples typically constitute only a small fraction of available data due to high experimental cost and safety constraints. To alleviate this limitation, a high-fidelity rotor–bearing dynamic model is developed by coupling an FEM-based flexible rotor with nonlinear Hertzian contact bearing dynamics, enabling realistic representation of distributed shaft flexibility, gyroscopic effects, and bearing nonlinearities for reliable fault data generation. Building on physics-informed features, EDANN is developed to effectively bridge the distribution gap between simulated and real-world data while providing interpretable fault diagnosis. EDANN successfully aligns simulation and real-world data domains. The model demonstrates robust and stable performance across a range of optimal hyperparameters, achieving a high average cross-domain diagnostic accuracy of 85.3%. Importantly, the explainable AI analysis feature of EDANN shows that the model’s decisions are driven by physically meaningful indicators such as orbit ellipticity and phase difference. These results demonstrate that EDANN provides a verifiable, accurate, and data-efficient solution, directly overcoming the trust and transparency barriers that currently hinder the industrial adoption of intelligent diagnostic systems and digital twins.

This study provides a comprehensive overview of challenges and advancements in vibration analysis for machinery operations under non-stationary and non-linear conditions. Non-stationary operation in machinery occurs when operating conditions such as speed, load, and environmental factors change over time. This results in dynamic behaviours that cause fluctuating vibration signals, making fault detection challenging with traditional methods that assume stationary conditions. The paper provides foundational insights and clear concepts on essential topics, including non-stationary operations in rotary machinery , vibration signals in non-stationary operations, cycle-stationary analysis, and the quantification of non-stationary operations. Further advancing, this paper explores the challenges and methodologies in condition-based monitoring for non-stationary machinery operations, focusing on the analysis of vibrational signals. It examines the complexities of working with non-stationary and cyclo -stationary signals and the limitations of traditional signal processing techniques . The study reviews classical time–frequency and advanced signal-processing methods, highlighting their advantages, drawbacks, and applicability in real-world scenarios. Additionally, it addresses the identification of defects across varying operational speeds, identifying gaps in current methodologies and suggesting potential avenues for future research. The paper also emphasizes the importance of transfer learning in non-stationary environments, analyzing various approaches and their effectiveness in improving monitoring performance. Lastly, it discusses the development of expertise and adoption pathways for AI-based predictive maintenance , offering insights into the practical integration of advanced technologies in industrial settings.