Hypertuned-YOLO for interpretable distribution power grid fault location based on EigenCAM

Stefenon, Stefano Frizzo; Seman, Laio Oriel; Klaar, Anne Carolina Rodrigues; Ovejero, Raúl García; Leithardt, Valderi Reis Quietinho

doi:10.1016/j.asej.2024.102722

Cited by 2 publications

(1 citation statement)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Abhiroop Bhattacharya et al [ 7 ] used a combination of current techniques in deep learning-based transformers, multilevel feature fusion, data augmentation, and object detection to quickly detect PCB board defects. Stefano Frizzo Stefenon et al [ 8 ] used a genetic algorithm to optimise the hyperparameters of the YOLO model for grid fault localisation, successfully improving performance metrics and reducing computational requirements. Fenglong Ding et al [ 9 ] employed transfer learning to apply a single-shot multibox detector (SSD) for wooden panel defect detection, utilising DenseNet as the backbone network instead of VGG16 and incorporating residual learning to mitigate feature information loss, thereby achieving wood defect detection.…”

Section: Introductionmentioning

confidence: 99%

Improved YOLOv8-Based Target Precision Detection Algorithm for Train Wheel Tread Defects

Wen,

Gao,

Luo

et al. 2024

Sensors

View full text Add to dashboard Cite

Train wheels are crucial components for ensuring the safety of trains. The accurate and fast identification of wheel tread defects is necessary for the timely maintenance of wheels, which is essential for achieving the premise of conditional repair. Image-based detection methods are commonly used for detecting tread defects, but they still have issues with the misdetection of water stains and the leaking of small defects. In this paper, we address the challenges posed by the detection of wheel tread defects by proposing improvements to the YOLOv8 model. Firstly, the impact of water stains on tread defect detection is avoided by optimising the structure of the detection layer. Secondly, an improved SPPCSPC module is introduced to enhance the detection of small targets. Finally, the SIoU loss function is used to accelerate the convergence speed of the network, which ensures defect recognition accuracy with high operational efficiency. Validation was performed on the constructed tread defect dataset. The results demonstrate that the enhanced YOLOv8 model in this paper outperforms the original network and significantly improves the tread defect detection indexes. The average precision, accuracy, and recall reached 96.95%, 96.30%, and 95.31%.

show abstract

Section: Introductionmentioning

confidence: 99%