计算机科学
背景(考古学)
卷积(计算机科学)
串联(数学)
特征(语言学)
棱锥(几何)
电池(电)
人工智能
路径(计算)
联营
融合
实时计算
卷积神经网络
特征提取
干扰(通信)
分割
节点(物理)
模式识别(心理学)
面子(社会学概念)
传感器融合
线性化
人工神经网络
自动化
作者
Yanchi Chen,Tianhong Pan,Jiaqiang Tian
标识
DOI:10.1088/1361-6501/ae09c6
摘要
Abstract Detecting defects in lithium batteries is critical to ensuring product consistency. However, existing visual models face significant challenges in identifying minute defects, dealing with intricate defect structures, and overcoming background interference in industrial environments. To address these practical challenges while meeting industrial production demands, a lightweight context fusion adaptive network for defect detection, named LACF-You Only Look Once (YOLO), is proposed in this work. LACF-YOLO replaces the conventional concatenation operation in the path aggregation feature pyramid network structure with a new context fusion method, effectively alleviating the degradation and loss of local and global features during feature fusion. Moreover, an adaptive defect detection module incorporated into the backbone network utilizing deformable convolution to accurately extract complex defect features. To further reduce the model’s parameter and computational load, a lightweight detection head based on depth-wise separable convolution is designed. Evaluated on a custom battery surface defects dataset, LACF-YOLO achieved a mean average precision of 87.6%, outperforming other models. Moreover, LACF-YOLO effectively balance accuracy, real-time performance, and parameter efficiency, establishing itself as the state-of-the-art technology for battery defect detection.
科研通智能强力驱动
Strongly Powered by AbleSci AI