MCDE-DETR: A Lightweight Real-Time Detection Model for Hot Forging Die Surface Defects

Accurate and efficient detection of hot forging die surface defects is essential for die condition assessment and stable forging production. However, automated visual inspection remains challenging because of large variations in defect scale and morphology, complex metallic textures and reflections, and weak fine-grained features. To address these challenges, we propose MCDE-DETR, a lightweight real-time detector based on RT-DETR-r18. Specifically, a Multi-Scale Edge Enhancement Network (MSENet) is designed as the backbone to strengthen multi-scale and edge-detail representation while reducing model complexity. Then, CGAFusion is introduced to enhance defect-related features and suppress background interference. DPCF is employed to preserve fine-grained information during cross-scale feature fusion. Finally, EDFFN is integrated into AIFI to improve frequency-aware feature representation with limited computational overhead. Experiments on a factory-collected dataset show that MCDE-DETR achieves 72.5% mAP50 and 46.6% mAP50:95, improving the baseline by 3.0 and 1.8 percentage points, respectively, while reducing parameters and GFLOPs by 25.1% and 10.4%. The model reaches 80.69 FPS, and Jetson Orin Nano deployment further demonstrates its practical feasibility for edge-based inspection.