Lightweight DETR for Small‐Target Defect Detection in Stators and Rotors of Pumped Storage Generators

Real‐time detection of micro‐defects in pumped storage generator stators and rotors remains challenging due to small‐target obscurity and edge deployment constraints. This paper proposes EdgeFault‐detection transformer (DETR), a lightweight transformer model that integrates three innovations: (1) dynamic geometric‐photometric augmentation for robustness, (2) a FasterNet backbone with Partial Convolution (PConv) that reduces the number of parameters by 40% (from 20 × 10 6 to 12 × 10 6 ), and (3) cross‐scale small‐object head enhancing defect localisation. Experiments on 8763 industrial images demonstrate 75.38% mAP@0.5 (+17.25% over RT‐DETR) and 49.3% mAP small (+42.9% from baseline). The model achieves 22 FPS on NVIDIA RTX A4000 GPUs (640 × 640 resolution), validating real‐time industrial applicability. Strategic computation allocation increases GFLOPs (giga floating‐point operations) by 16.4% (from 58.6 to 68.2) to prioritise safety–critical precision, justifying the trade‐off for detecting high‐risk anomalies (e.g., insulation cracks).