Feng Jianxin, Wang Jiahao, Zhao Xinyu, Liu Zhiguo, Ding Yuanming
Communication and Network Laboratory, Dalian University, Dalian, 116622, China.
School of Information Engineering, Dalian University, Dalian, 116622, China.
Sci Rep. 2024 Nov 26;14(1):29403. doi: 10.1038/s41598-024-80957-3.
Laser weld point detection is crucial in modern industrial manufacturing, yet it faces challenges such as a limited number of samples, uneven distribution, and diverse, irregular shapes. To address these issues, this paper proposes an innovative model, YOLO-Weld, which achieves lightweight design while enhancing detection accuracy. Firstly, a targeted data augmentation strategy is employed to increase both the quantity and diversity of samples from minority classes. Following this, a Diverse Class Normalization Loss (DCNLoss)function is designed to emphasize the importance of tail data in the model's training. Secondly, the Adaptive Hierarchical Intersection over Union Loss (AHIoU Loss)function is introduced, which assigns varying levels of attention to different Intersections over Union (IoU) samples, with a particular focus on moderate IoU samples, thereby accelerating the bounding box regression process. Finally, a lightweight multi-scale feature processing module, MSBCSPELAN, is proposed to enhance multi-scale feature handling while reducing the number of model parameters. Experimental results indicate that YOLO-Weld significantly improves the accuracy and efficiency of laser weld point detection, with mean Average Precision at 50 ([Formula: see text]) and mean Average Precision at 50:95 ([Formula: see text]) increasing by 15.6% and 15.8%, respectively. Additionally, the model's parameter count is reduced by 0.4 M, GFLOPS decreases by 1.1, precision improves by 4.3%, recall rises by 22.2%, and the F1 score increases by 15.1%.
激光焊点检测在现代工业制造中至关重要，但它面临着诸如样本数量有限、分布不均以及形状多样且不规则等挑战。为了解决这些问题，本文提出了一种创新模型YOLO-Weld，该模型在提高检测精度的同时实现了轻量化设计。首先，采用了有针对性的数据增强策略，以增加少数类样本的数量和多样性。在此之后，设计了一种多样类归一化损失（DCNLoss）函数，以强调尾部数据在模型训练中的重要性。其次，引入了自适应分层交并比损失（AHIoU Loss）函数，该函数对不同的交并比（IoU）样本分配不同程度的关注，特别关注中等IoU样本，从而加速边界框回归过程。最后，提出了一种轻量化多尺度特征处理模块MSBCSPELAN，以增强多尺度特征处理能力，同时减少模型参数数量。实验结果表明，YOLO-Weld显著提高了激光焊点检测的精度和效率，50%平均精度（[公式：见正文]）和50%至95%平均精度（[公式：见正文]）分别提高了15.6%和15.8%。此外，该模型的参数数量减少了0.4M，每秒浮点运算次数（GFLOPS）降低了1.1，精度提高了4.3%，召回率提高了22.2%，F1分数提高了15.1%。
