This paper proposes an enhanced YOLOv8 model with BiFPN-SimAM for precise defect detection in miniature capacitors. The model integrates the SimAM attention mechanism and BiFPN architecture to improve feature recognition and multi-scale feature fusion, while the WISE-IOU loss function enhances generalization and robustness. A dataset of 1358 images with four types of micro-capacitor defects was constructed. Experimental results show the model achieves 95.8% mAP@0.5, a 9.5% improvement over the original YOLOv8. The model maintains real-time detection speed, making it suitable for industrial applications. The contributions include algorithmic enhancement, performance efficiency, and dataset compilation. The study demonstrates the effectiveness of the enhanced model in detecting small defects in micro-capacitors, with significant improvements in accuracy and robustness. The model outperforms other algorithms like SSD, Faster R-CNN, and YOLOv5n, YOLOv7-tiny in detection accuracy and speed. The results highlight the model's ability to detect subtle defects, making it a valuable tool for quality control in electronics manufacturing. The study also addresses challenges in data scarcity and model generalization, offering a scalable solution for real-world applications.This paper proposes an enhanced YOLOv8 model with BiFPN-SimAM for precise defect detection in miniature capacitors. The model integrates the SimAM attention mechanism and BiFPN architecture to improve feature recognition and multi-scale feature fusion, while the WISE-IOU loss function enhances generalization and robustness. A dataset of 1358 images with four types of micro-capacitor defects was constructed. Experimental results show the model achieves 95.8% mAP@0.5, a 9.5% improvement over the original YOLOv8. The model maintains real-time detection speed, making it suitable for industrial applications. The contributions include algorithmic enhancement, performance efficiency, and dataset compilation. The study demonstrates the effectiveness of the enhanced model in detecting small defects in micro-capacitors, with significant improvements in accuracy and robustness. The model outperforms other algorithms like SSD, Faster R-CNN, and YOLOv5n, YOLOv7-tiny in detection accuracy and speed. The results highlight the model's ability to detect subtle defects, making it a valuable tool for quality control in electronics manufacturing. The study also addresses challenges in data scarcity and model generalization, offering a scalable solution for real-world applications.