In the fault diagnosis of planetary gearboxes under varying operating conditions, fault features are often submerged and difficult to characterize. To address this issue, this paper proposes a fault diagnosis method for planetary gearboxes based on an Attention Mechanism Wide-scale Multi-channel Temporal Convolutional Network (AWM-TCN). This method introduces an attention mechanism into the TCN framework, ensuring the model learns the spatiotemporal characteristics of fault signals while enhancing the importance of fault-related features. The experimental section innovatively employs three different validation methods for multi-angle evaluation of the model, discusses the impact of different structures on the proposed model, and compares it with various classical models. The results indicate that AWM-TCN can achieve effective diagnosis of planetary gearboxes under varying conditions and demonstrates rapid responsiveness.