融合注意力机制的铝型材缺陷检测研究

打开文本图片集

中图分类号：TP391.4 文献标志码：A 文章编号：1008-0562（2026）02-0249-08

Abstract：In the field of industrial material production and management，traditional detection methodsare difficult to meet the diverse detection requirements for surface coating cracks and other defects of aluminum profiles.Moreover，existing detection models have problems of missed detection and false detectionof small targets.This paper proposes a surface defect detection method for aluminum profiles based on YOLOv8n-SE.By embedding the SEatention mechanism in the neck network oftheYOLOv8n model，the feature extraction ability is enhanced，improving the positioning accuracy and defect sensitivity of the defect area.Experiments were conducted using an aluminum profile defect dataset，and the proposed method wascompared with lightweight models such as FasterR-CNN and YOLOv5n combined with diffrent attention mechanisms.The research results showthat the average precision （mAP） of the improved model reaches 75.0% a 4.2% higher than the original YOLOv8n model， with the number of parameters remaining basically unchanged and the inference speed only decreasing by 0.3% .The improved YOLOv8n model with the embedded SE attention mechanism can effectively improve the recognition efectof surface defects of aluminum profiles，solve the problem of missed detection and false detection of smalltargets，and maintain the eficient inference advantage of lightweight models，making it suitable for the defect detection requirements of aluminum profiles in industrial scenarios.

Keywords： defect detection; aluminum profiles; YOLOv8 model; SE attention mechanism; small target detection

0 引言在工业4.0与智能制造深度融合的背景下，铝型材工件表面缺陷检测技术面临着新的要求与挑战。（剩余13863字）