YOLOv8改進策略在焊接外部缺陷檢測模型中的應(yīng)用研究

打開文本圖片集

中圖分類號：TP391.4；TP183 文獻標識碼：A 文章編號：2096-4706（2025）12-0068-06

Research on the Application of YOLOv8 Improvement Strategy in Welding External Defect Detection Model

ZHU Yonghong，YANG Kaifu （Jingdezhen Ceramic University，Jingdezhen 333403，China）

Abstract： Aiming at the challenges of missed detection，false detection and arbitrary distribution of defect angles in smalltargetdefectdetectioninwelding extemaldefectimagedetection，anoptimizedand improvedmodelbasedonYOLOv8， YOLO-weld，isproposed.FirstlySPF-weldandC2f_DBB_CBAMmodulesaredesigned tonhancethecontextinfoation agregationabilityandmulti-scale featurefusioneffectofYOLO-weldmodel.Secondly，theOBBdetectionheadisintroduced toaccuratelycapturedirectionaldefects，soastoimprovethedetectionacuracy.Finalytheexperimentalresultshowthat compared with the YOLOv8 model， the YOLO-weld model improves the accuracy，recall，harmonic mean （F1） and mAP @0.5 by 3.2% 0 2.6% 0 4.0% and 3.9% ，respectively，which fully proves the effectiveness of the YOLO-weld model improvement.

Keywords： welding external defect identification; non-destructive testing; YOLOv8; C2f_DBB

0 引言

隨著現(xiàn)代工業(yè)的迅猛發(fā)展，焊接技術(shù)已在眾多工業(yè)領(lǐng)域中發(fā)揮著不可或缺的作用，保障焊接結(jié)構(gòu)的堅固性和穩(wěn)定性，已成為工業(yè)發(fā)展中的關(guān)鍵議題。（剩余8290字）