The spatiotemporal band-gated modal decomposition method and its application in compound fault diagnosis of gearbox

Abstract

Mechanical systems are characterized by complex structures, multi-source vibrations, and strong coupling. Existing multi-channel signal analysis methods do not fully consider the characteristics of fault mechanisms and thus struggle to achieve decoupling and feature extraction for compound faults. To tackle this challenge, this paper proposes a novel multi-channel signal analysis method—Spatiotemporal band-gated modal decomposition (SBGMD). The method consists of three main steps: First, SBGMD decomposes multi-channel signals into temporal and spatial modes, establishing a spatiotemporal representation structure for the signals. Second, by introducing a nonlinear matching pursuit mechanism, the method applies time-varying frequency modulation constraints to the temporal modes, thereby extracting physically interpretable modal components. Finally, by leveraging the unique frequency evolution characteristics of mechanical faults, SBGMD innovatively constructs a band-gated structure. Within this structure, the method iteratively searches for the optimal distribution of sidebands, achieving precise separation of strongly coupled fault features and ultimately extracting fault modal components with interpretable mechanisms. As a multi-channel signal processing method that combines band-gated with spatiotemporal modal decomposition, SBGMD proposes a decomposition strategy based on band-gated characteristics. This strategy closely matches the typical frequency domain manifestations of faults and possesses strong capabilities for feature interpretation and weak signal mining. Therefore, the method effectively extracts and separates multi-source complex coupled feature signals. When being applied to the simulation and experimental signal analysis of compound fault diagnosis in gearboxes, the method exhibits good robustness and superiority in feature extraction and fault identification. Thus, it offers a novel solution for the fault diagnosis of complex mechanical systems.