Potassium-ion batteries(KIBs)have been seen as a competitive alternative to lithium-ion batteries(LIBs)due to their natural abundance,low cost and rocking chair-like operating mechanism similar to LIBs.Soft carbon has...Potassium-ion batteries(KIBs)have been seen as a competitive alternative to lithium-ion batteries(LIBs)due to their natural abundance,low cost and rocking chair-like operating mechanism similar to LIBs.Soft carbon has a lower voltage plateau compared to hard carbon and an easily modulated lattice structure compared to graphite,which provides particular advantages in KIBs anodes.Pitch has attracted much attention as a simple,readily available and inexpensive precursor for soft carbon,but its structure is easily damaged during cycling.Herein,the flexible film Pitch@CNF are prepared by uniformly winding reticulated carbon fibers on the surface of pitch-soft carbon via electrostatic spinning technique,which not only enables the pitch to maintain its structure well during cycling and withstand the volume expansion upon K^(+) insertion,but also is conducive to ionic transport of the three-dimensional reticulated structure.Meanwhile,the abundant pores on the carbon fibers can provide more K^(+) active sites.The prepared flexible self-supporting films can be used directly as electrodes without the addition of binders and conductive agents.The reversible capacity is 290 mAh·g^(-1)at a current density of 0.1 A·g^(-1),and the capacity retention rate is 83%after 500 cycles.展开更多
提出一种基于Faster RCNN(Faster Region with Convolutional Neural Networks)的电路板缺陷图像自动检测方法。该方法首先应用ResNet50网络作为主干网络以提取缺陷图像特征;然后针对电路板图像中缺陷的极端长宽比特点,提出基于特征金...提出一种基于Faster RCNN(Faster Region with Convolutional Neural Networks)的电路板缺陷图像自动检测方法。该方法首先应用ResNet50网络作为主干网络以提取缺陷图像特征;然后针对电路板图像中缺陷的极端长宽比特点,提出基于特征金字塔的区域推荐网络,得到多尺度特征融合图并生成建议框;最后,通过对感兴趣区域进行池化处理,并结合后续网络实现对电路板图像上缺陷的快速检测。试验证明,所提算法能够快速定位出电路板图像中的各种缺陷,并能实现准确的自动分类识别。展开更多
文摘Potassium-ion batteries(KIBs)have been seen as a competitive alternative to lithium-ion batteries(LIBs)due to their natural abundance,low cost and rocking chair-like operating mechanism similar to LIBs.Soft carbon has a lower voltage plateau compared to hard carbon and an easily modulated lattice structure compared to graphite,which provides particular advantages in KIBs anodes.Pitch has attracted much attention as a simple,readily available and inexpensive precursor for soft carbon,but its structure is easily damaged during cycling.Herein,the flexible film Pitch@CNF are prepared by uniformly winding reticulated carbon fibers on the surface of pitch-soft carbon via electrostatic spinning technique,which not only enables the pitch to maintain its structure well during cycling and withstand the volume expansion upon K^(+) insertion,but also is conducive to ionic transport of the three-dimensional reticulated structure.Meanwhile,the abundant pores on the carbon fibers can provide more K^(+) active sites.The prepared flexible self-supporting films can be used directly as electrodes without the addition of binders and conductive agents.The reversible capacity is 290 mAh·g^(-1)at a current density of 0.1 A·g^(-1),and the capacity retention rate is 83%after 500 cycles.
文摘提出一种基于Faster RCNN(Faster Region with Convolutional Neural Networks)的电路板缺陷图像自动检测方法。该方法首先应用ResNet50网络作为主干网络以提取缺陷图像特征;然后针对电路板图像中缺陷的极端长宽比特点,提出基于特征金字塔的区域推荐网络,得到多尺度特征融合图并生成建议框;最后,通过对感兴趣区域进行池化处理,并结合后续网络实现对电路板图像上缺陷的快速检测。试验证明,所提算法能够快速定位出电路板图像中的各种缺陷,并能实现准确的自动分类识别。
