A data-driven fault diagnosis of high speed maglev train levitation system

The levitation system is a crucial component of a maglev train as it is responsible for levitating the train body above the track. Real-time diagnosis of faults in the levitation system is essential for commercial operational purposes. Despite extensive research on the mechanism of the levitation system, it is challenging to obtain an accurate system model due to unavoidable noise and disturbances. To address this issue, this paper proposes a fault diagnosis method for the maglev train levitation system. This method combines model-based fault diagnosis with a data-based implementation approach to maximize the benefits of both approaches while considering system noise and model uncertainty. Additionally, a secondary confirmation of fault isolation results is proposed to improve the reliability of fault diagnosis and minimize the effect of false alarms. Finally, a subsequent processing of fault data is recommended to enrich fault analysis methods.