ELD-YOLO: An explainable edge-deployable intelligent framework for low-contrast radiographic weld defect inspection

Low-contrast radiographic weld defects are difficult to detect automatically because small and weakly bounded indications are easily confused with weld texture, image-quality markers and background intensity variation. This study presents ELD-YOLO, an explainable and edge-deployable YOLO framework for detecting cracks, lack of fusion, lack of penetration, porosity and slag inclusion in plate-weld radiographs. The framework first localizes the weld region and then performs overlapping sliding-window defect detection on local weld patches. To improve sensitivity to faint and small defects, a Dual Feature Cross Attention with Intensity Enhancement (DFCA-IE) module is embedded in YOLO11n to couple cross-level feature interaction with defect-related intensity enhancement, while Grad-CAM is used to inspect whether model responses align with defect regions. A dataset was constructed from 68 public GDXray images and 374 industrial radiographic weld images, producing 3748 augmented defect samples after annotation, weld-region extraction and augmentation. On the validation set, ELD-YOLO achieved a precision of 0.947, recall of 0.856, F1-score of 0.900, mAP@50 of 0.918 and mAP@50:95 of 0.627, with 4.02M parameters, 15.7 GFLOPs and 156.8 FPS. Compared with the strongest P5 baseline, precision, recall and F1-score increased by 11.5%, 19.2% and 16.9%, respectively. Grad-CAM heatmaps were concentrated around detected defect regions. Raspberry Pi 5 testing on 11 images showed standalone CPU-based execution with 606.32 MB average peak memory usage and stable short-run temperature, supporting edge-side radiographic weld inspection.