A Novel Ramanujan Digital Twin for Periodic Fault Feature Extraction of Rotating Machines

The signal-processing and intelligent diagnostic and monitoring methods for rotating machines usually depend on preset parameters. Moreover, many of these methods have difficulty in achieving ideal health monitoring effect and fault prediction results with strong noise interference. To overcome these limitations, a novel digital twin architecture called the Ramanujan digital twin (RDT) is composed. This architecture uses the Ramanujan periodic transform (RPT) as its computational core to detect the potential fault signatures in each monitoring frame. The phenomenal faulty simulation model with high fidelity to the real-time potential fault features of the rotating machines is constructed to avoid drawbacks of the physics-based simulation, such as the complicated modeling process and the high-computation consumption. This simulation signal will function as the virtual entity of the RDT, providing guidance information, with which the proposed method will no longer depend on the preset parameters. The effectiveness and robustness of the RDT are validated through experimental cases.