Progress on the application of deep learning in gearbox fault diagnosis

Abstract As a critical component in industrial machinery systems, gearboxes demand robust fault diagnosis solutions to ensure operational safety, energy efficiency, and sustainable manufacturing practices. Deep learning (DL) has emerged as a transformative approach for intelligent fault identification, demonstrating superior capabilities in processing complex vibration signatures compared to conventional methods. This review systematically examines DL applications in gearbox diagnostics through dual perspectives of theoretical foundations and industrial implementations. Six principal DL architectures are critically analyzed, including their advanced variants optimized for mechanical signal processing. The study systematically compares these architectures across diagnostic capabilities, computational demands, and implementation constraints. This review identifies promising research directions to address the current challenges in gearbox fault diagnosis. It aims to establish strategic research pathways that bridge the existing gap between theoretical models and industrial requirements, thereby enhancing the predictive maintenance framework for next-generation intelligent manufacturing systems.