Reliable recognition of fault type and assessment of fault severity are essential for decision making in condition-based maintenance of rotating machinery. In engineering practice, the mechanical systems of rotating machinery are often subject to hybrid faults on the same component or different components. The concurrence of multiple faults makes the fault detection, in particular, and the examination of both the fault types and severities more challenging.

Popular intelligent algorithms, for example, artificial neural networks, have been introduced into multifault pattern recognition. One can hardly understand how the neural networks work due to lack of “physical meanings.” One potential solution is a multimodal, integrated approach, which decouples the hybrid faults by extracting submodes with each corresponding to a single fault. Then the multifault detection, diagnosis, and prognosis can be effectively performed.

The purpose of this special issue is to publish high-quality research papers as well as review articles addressing recent advances on multifault detection, diagnosis, and prognosis for rotating machinery. We welcome original, high-quality contributions that are not yet published or that are not currently under review by other journals or peer-reviewed conferences.

Potential topics include but are not limited to the following:

• Wavelet based decoupling techniques
• Empirical mode decomposition based decoupling techniques
• Order tracking based decoupling techniques
• Sparse decomposition based decoupling techniques
• Blind source separation (BSS) based decoupling techniques
• Intelligent theory based decoupling techniques
• Novel multifault prognosis techniques
• Remaining life prediction techniques
• Practical case studies on multifault diagnosis and prognosis