Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order t...Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order to solve this problem,we propose a new method,which combined the lightweight network mobile vision transformer(Mobile Vi T)with the convolutional block attention module(CBAM)mechanism and the new regression loss function.This method needed less computation resources,making it more suitable for embedded edge detection devices.Meanwhile,the new loss function improved the positioning accuracy of the bounding box and enhanced the robustness of the model.In addition,experiments on public datasets demonstrate that the improved model achieves an average accuracy of 87.9%across six typical defect detection tasks,while reducing computational costs by nearly 90%.It significantly reduces the model's computational requirements while maintaining accuracy,ensuring reliable performance for edge deployment.展开更多
The microstructures and mechanical properties of ferrite-based lightweight steel with different compositions were investigated by tensile test,scanning electron microscopy（SEM）,transmission electron microscopy（TEM...The microstructures and mechanical properties of ferrite-based lightweight steel with different compositions were investigated by tensile test,scanning electron microscopy（SEM）,transmission electron microscopy（TEM）,X-ray diffraction（XRD）and thermodynamic calculation（TC）.It was shown that the ferrite-based lightweight steels with 5wt.%or 8wt.%Al were basically composed of ferrite,austenite andκ-carbide.As the annealing temperature increased,the content of the austenite in the steel gradually increased,while theκ-carbide gradually decomposed and finally disappeared.The mechanical properties of the steel with 5wt.%Al and 2wt.%Cr,composed of ferrite and Cr7C3carbide at different annealing temperatures,were significantly inferior to those of others.The steel containing 5wt.%Al,annealed at 820°C for 50sthen rapidly cooled to 400°C and held for 180s,can obtain the best product of strength and elongation（PSE）of 31242MPa·%.The austenite stability of the steel is better,and its PSE is higher.In addition,the steel with higher PSE has a more stable instantaneous strain hardening exponent（n value）,which is mainly caused by the effect of transformation induced plasticity（TRIP）.When theκ-carbide or Cr7C3carbide existed in the microstructure of the steel,there was an obvious yield plateau in the tensile curve,while its PSE decreased significantly.展开更多
基金supported by the National Natural Science Foundation of China(Nos.62373215,62373219 and 62073193)the Natural Science Foundation of Shandong Province(No.ZR2023MF100)+1 种基金the Key Projects of the Ministry of Industry and Information Technology(No.TC220H057-2022)the Independently Developed Instrument Funds of Shandong University(No.zy20240201)。
文摘Current you only look once(YOLO)-based algorithm model is facing the challenge of overwhelming parameters and calculation complexity under the printed circuit board(PCB)defect detection application scenario.In order to solve this problem,we propose a new method,which combined the lightweight network mobile vision transformer(Mobile Vi T)with the convolutional block attention module(CBAM)mechanism and the new regression loss function.This method needed less computation resources,making it more suitable for embedded edge detection devices.Meanwhile,the new loss function improved the positioning accuracy of the bounding box and enhanced the robustness of the model.In addition,experiments on public datasets demonstrate that the improved model achieves an average accuracy of 87.9%across six typical defect detection tasks,while reducing computational costs by nearly 90%.It significantly reduces the model's computational requirements while maintaining accuracy,ensuring reliable performance for edge deployment.
基金supported by the Shanghai Municipal Natural Science Foundation(Grant No.17ZR1410400)the Shanghai Municipal Science and Technology Commission(Grant Nos.15DZ2260300,15DZ2260301)
文摘The microstructures and mechanical properties of ferrite-based lightweight steel with different compositions were investigated by tensile test,scanning electron microscopy（SEM）,transmission electron microscopy（TEM）,X-ray diffraction（XRD）and thermodynamic calculation（TC）.It was shown that the ferrite-based lightweight steels with 5wt.%or 8wt.%Al were basically composed of ferrite,austenite andκ-carbide.As the annealing temperature increased,the content of the austenite in the steel gradually increased,while theκ-carbide gradually decomposed and finally disappeared.The mechanical properties of the steel with 5wt.%Al and 2wt.%Cr,composed of ferrite and Cr7C3carbide at different annealing temperatures,were significantly inferior to those of others.The steel containing 5wt.%Al,annealed at 820°C for 50sthen rapidly cooled to 400°C and held for 180s,can obtain the best product of strength and elongation（PSE）of 31242MPa·%.The austenite stability of the steel is better,and its PSE is higher.In addition,the steel with higher PSE has a more stable instantaneous strain hardening exponent（n value）,which is mainly caused by the effect of transformation induced plasticity（TRIP）.When theκ-carbide or Cr7C3carbide existed in the microstructure of the steel,there was an obvious yield plateau in the tensile curve,while its PSE decreased significantly.
