The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly...The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.展开更多
We report the fabrication of 4-inch nano patterned wafer by two-beam laser interference lithography and analyze the uniformity in detail. The profile of the dots array with a period of 800 nm divided into five regions...We report the fabrication of 4-inch nano patterned wafer by two-beam laser interference lithography and analyze the uniformity in detail. The profile of the dots array with a period of 800 nm divided into five regions is characterized by a scanning electron microscope. The average size in each region ranges from 270 nm to 320 nm,and the deviation is almost 4%, which is approaching the applicable value of 3% in the industrial process. We simulate the two-beam laser interference lithography system with MATLAB software and then calculate the distribution of light intensity around the 4 inch area. The experimental data fit very well with the calculated results. Analysis of the experimental data and calculated data indicates that laser beam quality and space filter play important roles in achieving a periodical nanoscale pattern with high uniformity and large area. There is the potential to obtain more practical applications.展开更多
To meet the development trend of multi-bar warp knit-ting machine towards high-speed,advanced technologyand computer control and the requirements of variousproducts with small quantity,there are many researcheson the ...To meet the development trend of multi-bar warp knit-ting machine towards high-speed,advanced technologyand computer control and the requirements of variousproducts with small quantity,there are many researcheson the computer-aided pattern design of multi-barwarp knitted fabrics.In terms of the special propertiesof the computer-aided pattern design of multi-barwarp knitted fabrics,the Object Oriented Program(OOP)programming-Object Windows class Library(OWL)programming is selected.According to thecharacters of the OWL programming,various functionsare defined.Pattern design and technical parameters canbe output,which offers a great convenience for the fac-tory.展开更多
基金National Key Research and Development Project,China(No.2018YFB1308800)。
文摘The background pattern of patterned fabrics is complex,which has a great interference in the extraction of defect features.Traditional machine vision algorithms rely on artificially designed features,which are greatly affected by background patterns and are difficult to effectively extract flaw features.Therefore,a convolutional neural network(CNN)with automatic feature extraction is proposed.On the basis of the two-stage detection model Faster R-CNN,Resnet-50 is used as the backbone network,and the problem of flaws with extreme aspect ratio is solved by improving the initialization algorithm of the prior frame aspect ratio,and the improved multi-scale model is designed to improve detection of small defects.The cascade R-CNN is introduced to improve the accuracy of defect detection,and the online hard example mining(OHEM)algorithm is used to strengthen the learning of hard samples to reduce the interference of complex backgrounds on the defect detection of patterned fabrics,and construct the focal loss as a loss function to reduce the impact of sample imbalance.In order to verify the effectiveness of the improved algorithm,a defect detection comparison experiment was set up.The experimental results show that the accuracy of the defect detection algorithm of patterned fabrics in this paper can reach 95.7%,and it can accurately locate the defect location and meet the actual needs of the factory.
基金Supported by the Scientific Equipment Research Program of Chinese Academy of Sciences under Grant No 2014Y4201449
文摘We report the fabrication of 4-inch nano patterned wafer by two-beam laser interference lithography and analyze the uniformity in detail. The profile of the dots array with a period of 800 nm divided into five regions is characterized by a scanning electron microscope. The average size in each region ranges from 270 nm to 320 nm,and the deviation is almost 4%, which is approaching the applicable value of 3% in the industrial process. We simulate the two-beam laser interference lithography system with MATLAB software and then calculate the distribution of light intensity around the 4 inch area. The experimental data fit very well with the calculated results. Analysis of the experimental data and calculated data indicates that laser beam quality and space filter play important roles in achieving a periodical nanoscale pattern with high uniformity and large area. There is the potential to obtain more practical applications.
文摘To meet the development trend of multi-bar warp knit-ting machine towards high-speed,advanced technologyand computer control and the requirements of variousproducts with small quantity,there are many researcheson the computer-aided pattern design of multi-barwarp knitted fabrics.In terms of the special propertiesof the computer-aided pattern design of multi-barwarp knitted fabrics,the Object Oriented Program(OOP)programming-Object Windows class Library(OWL)programming is selected.According to thecharacters of the OWL programming,various functionsare defined.Pattern design and technical parameters canbe output,which offers a great convenience for the fac-tory.
