基于改進(jìn)DiffusionDet的印刷電路板缺陷檢測(cè)研究

打開(kāi)文本圖片集

Research on PCB Defect Detection Based on Improved DiffusionDet

WangXiuyou，HuangGuangren，LiuHuaming，unHaoyu （Fuyang Normal University，F(xiàn)uyang236037，China）

【Abstract]Defects inprintedcircuitboards （PCBs）candirectlyimpairthe performanceof electronicdevices，yeteffective lydetectingpotentialPCBdefectsremainsapersistentchallngeintheindustry.Tosolvethisproblem，animprovedalgo rithmbasedonDifusionDetisproposedtodetectPCBdefects directlywithoutrelyingonthequeryof experienceobjectsor learnableobjects.Thekeyimprovements includethat，firstlyObjectDetectionConvolution（ODConv）isusedtoeplacepart ofthestaticconvolution kernelofthefeatureextractionnetwork，expandingthelearningdimensionofconvolutionaloperation，soastoobtainfeaturemapsthataremoreconducivetodefectdetection，andsecondly，theGUlossfunctionisusedto replacetheoriginalIoUlossfunctiontoimprovethemodel'sabilitytooptimize thepositionofpreselectedframes.Theexperimental results show that the improved DiffusionDet achieves a mean Average Precision （mAP） of 98.83% ，up from the original 98.12% ，showing better performance in PCB defect detection tasks.

【Key words] printed circuit board; defect detection; DiffusionDet; ODConv; GIoU

[中圖分類(lèi)號(hào)］TN41 [文獻(xiàn)標(biāo)識(shí)碼]A

[文章編號(hào)]1674-3229（2025）02-0057-07

0 引言

印刷電路板承載著電子元件間信號(hào)傳輸、電源供應(yīng)和數(shù)據(jù)處理等重要功能。（剩余9985字）