Al-Si closed-cell aluminum foam bare boards of 1 240 mm×1 100 mm with different densities and thicknesses wereprepared by molten body transitional foaming process.The sound reduction index(R)of Al-Si closed-cell ...Al-Si closed-cell aluminum foam bare boards of 1 240 mm×1 100 mm with different densities and thicknesses wereprepared by molten body transitional foaming process.The sound reduction index(R)of Al-Si closed-cell aluminum foam bareboards was investigated experimentally under different frequencies(100-4 000 Hz).It is found that sound reduction index(R)issmall under low frequencies,large under high frequencies and is controlled by different mechanisms.The sound insulation propertybasically conforms with the monolayer board sound insulation theory.The sound reduction index(R)increases with the even growthof thickness and density,but its rising trend is tempered.The single number sound reduction indexes(RW)of specimen with thicknessof 20 cm and density of 0.51 g/cm3are 30.8 dB and 33 dB respectively,which demonstrates good sound insulation property forlightmass materials.展开更多
PCB(Printed Circuit Board)裸板缺陷采用人工目视和电气特性等传统检测方法存在检测效率低、误检率高、成本高、劳动强度大、接触式飞针易造成损伤等问题。提出将YOLO(You Only Look Once)v4引入到PCB裸板缺陷检测,采用Canopy+K-means...PCB(Printed Circuit Board)裸板缺陷采用人工目视和电气特性等传统检测方法存在检测效率低、误检率高、成本高、劳动强度大、接触式飞针易造成损伤等问题。提出将YOLO(You Only Look Once)v4引入到PCB裸板缺陷检测,采用Canopy+K-means聚类改进YOLOv4中K-means聚类获取先验框。将改进的YOLOv4应用到PCB裸板的短路、开路、缺口、毛刺、焊点漏焊、余铜等缺陷检测中,开发了软硬件平台,形成了高精度、高检测速度的PCB裸板缺陷检测系统。基于PCB_DATASET数据集将该文提出的方法与已有的基于深度学习的PCB裸板缺陷检测方法进行了对比实验和分析。实验结果表明,该文提出方法的缺陷检测mAP(mean Average Precision)值达到了99.48%,检测速度为37.09帧/秒,相较于目前已有的基于深度学习的PCB裸板缺陷检测方法,不仅检测速度更快,而且检测精确度更高。展开更多
基金Project(2002AA334060)supported by Hi-tech Research and Development Program of China
文摘Al-Si closed-cell aluminum foam bare boards of 1 240 mm×1 100 mm with different densities and thicknesses wereprepared by molten body transitional foaming process.The sound reduction index(R)of Al-Si closed-cell aluminum foam bareboards was investigated experimentally under different frequencies(100-4 000 Hz).It is found that sound reduction index(R)issmall under low frequencies,large under high frequencies and is controlled by different mechanisms.The sound insulation propertybasically conforms with the monolayer board sound insulation theory.The sound reduction index(R)increases with the even growthof thickness and density,but its rising trend is tempered.The single number sound reduction indexes(RW)of specimen with thicknessof 20 cm and density of 0.51 g/cm3are 30.8 dB and 33 dB respectively,which demonstrates good sound insulation property forlightmass materials.
文摘PCB(Printed Circuit Board)裸板缺陷采用人工目视和电气特性等传统检测方法存在检测效率低、误检率高、成本高、劳动强度大、接触式飞针易造成损伤等问题。提出将YOLO(You Only Look Once)v4引入到PCB裸板缺陷检测,采用Canopy+K-means聚类改进YOLOv4中K-means聚类获取先验框。将改进的YOLOv4应用到PCB裸板的短路、开路、缺口、毛刺、焊点漏焊、余铜等缺陷检测中,开发了软硬件平台,形成了高精度、高检测速度的PCB裸板缺陷检测系统。基于PCB_DATASET数据集将该文提出的方法与已有的基于深度学习的PCB裸板缺陷检测方法进行了对比实验和分析。实验结果表明,该文提出方法的缺陷检测mAP(mean Average Precision)值达到了99.48%,检测速度为37.09帧/秒,相较于目前已有的基于深度学习的PCB裸板缺陷检测方法,不仅检测速度更快,而且检测精确度更高。
