Abstract:

To address the challenges such as low detection efficiency, difficulties in identifying small defects, and poor accuracy in detecting surface defects on automotive wheel hubs, a lightweight neural network called CCL-YOLOv8 was proposed based on an improved YOLOv8n architecture. A synergistic improvement in both detection accuracy and efficiency was achieved through a three-stage model optimization strategy. A convolutional attention fusion module was introduced, which integrated convolution operations with self-attention mechanisms, thereby enhancing the model's ability to capture local features of small defects while perceiving global context under low signal-to-noise ratio conditions. A C2f-Star module was constructed to reduce computational overhead and enhance feature expression by optimizing feature interaction through element-wise multiplication. A lightweight shared detail-enhanced convolution detection head was designed to reduce the number of parameters and computational requirements and ensure high-precision detection by combining shared convolution and differential convolution. Experimental results demonstrate that the CCL-YOLOv8 algorithm significant enhancements are achieved in detection accuracy, model lightweighting, and computational efficiency compared to existing algorithms. Consequently, this approach effectively addresses the technical challenges in detecting surface defects on automotive wheel hubs and provides an efficient, lightweight, and precise solution for industrial real-time detection.

Key words: automotive wheel hub, CCL-YOLOv8, defect detection, model lightweighting, attention mechanism