Variable reluctance generator assisted intelligent monitoring and diagnosis of wind turbine spherical roller bearings

Abstract

The development of intelligent spherical roller bearings (ISRBs) with self-powered, sensing, and diagnostic capabilities is crucial for enhancing wind turbine platform operation and maintenance. This study introduces a finite-number roller-based variable reluctance generator (FR-VRG) as a promising approach for ISRB construction. In the FR-VRG, the limited number of bearing rollers creates a gap between adjacent rollers, allowing each roller to periodically pass through a magnetic circuit consisting of a coil, iron core, and permanent magnet. This movement causes a variable reluctance effect, which induces current in the coil, achieving electromechanical energy conversion. Since the coil and permanent magnet are fixed and do not rotate, they have minimal impact on the rotating parts of the bearing. Key design parameters, including coil turns, coil-to-roller distance, and iron core material, were tested and analyzed for their effect on the FR-VRG’s self-power performance. We applied the fast Fourier transform and deep learning methods to classify typical bearing faults, and the system achieved an accuracy of 94.05%. The FR-VRG’s power generation mechanism was verified through theoretical and simulation analyses. Additionally, the self-sensing and diagnosis capability of the ISRB with the FR-VRG was verified on a wind turbine test setup, where sensing tests were conducted at variable speeds. The proposed FR-VRG provides an effective alternative for constructing intelligent wind turbine operation and maintenance systems.