Zero-sample diagnostic methods have gained recognition in addressing the scarcity of gearbox fault samples, thereby being regarded as a promising technique to guarantee gearbox safety. However, historical zero-sample approaches typically neglect the use of multi-modal non-contact sensing data and rarely consider the interpretability of the diagnostic process. This oversight limits their application in industrial environments that require high reliability or operate under extreme conditions. Therefore, this paper presents a composite neuro-fuzzy system-guided cross-modal zero-sample diagnostic framework, termed FCZD-IA, which employs infrared thermography and acoustic data to monitor gearbox conditions. Specifically, FCZD-IA uses a proposed composite neural system as a decision-maker in the diagnostic task, while integrating a deep backbone network to discriminatively learn high-level fault features from multi-modal data. Moreover, a specific training strategy is designed to guide the learning process of the FCZD-IA to promote robust and interpretable zero-sample diagnostics. Comprehensive experimental results validate the effectiveness of the proposed framework and its superiority over other competitive methods.

Magnetic bearings use magnetic forces to support various machine components. Because of the non-contact nature of this type of suspension, magnetic bearing technology offers a number of significant advantages over conventional bearings, such as rolling element and fluid film bearings. An active magnetic bearing basically consists of an electromagnetic actuator, position sensors, power amplifiers, and a feedback controller. All of these components are characterized by nonlinear behavior and therefore the entire system is inherently nonlinear. However, in simulations of the dynamic behavior of magnetic bearing systems, the nonlinearities are usually neglected to simplify the analysis and only linear models are used. Moreover, many control techniques currently used in magnetic bearing systems are generally designed by ignoring nonlinear effects. The main reason for simplification is the intractability of the complexity of the actual model. In fact, the inherent nonlinear properties of magnetic bearing systems can lead to dynamic behavior of a magnetically suspended rotor that is distinctly different from that predicted using a simple linearized model. Therefore, the nonlinearities should be taken into account. This literature review is focused on the nonlinear dynamics of magnetic bearing systems and it provides background information on analytical methods, nonlinear vibrations resulting from a rotor contacting auxiliary bearings, and other active topics of research involving the nonlinear properties of magnetic bearing systems, such as nonlinear self-sensing magnetic bearings and nonlinear control of magnetic bearings. The review concludes with a brief discussion on current and possible future directions for research on the nonlinear dynamics of magnetic bearing systems.