The purpose of this thesis is to use drones and machine learning algorithms for automating crack detection in tunnel systems.With the high resolution RGB cameras and LiDAR sensor in drones,you get the imagery and stru...The purpose of this thesis is to use drones and machine learning algorithms for automating crack detection in tunnel systems.With the high resolution RGB cameras and LiDAR sensor in drones,you get the imagery and structural data required to inspect tunnels.The images are then fed through CNNs together with SVMs for detecting and classification cracks in concrete and other surfaces.With this automated mechanism,the process will no longer need manual effort,and the inspection will be more precise and safer.The study shows the efficiency of this hybrid approach,which has 92%detection rate,much better than traditional inspection.And it is also very good at reducing false positives,and produces more trustworthy results.Crack severity is sorted into hairline,medium and deep cracks to make the process of maintenance and repairs easier.According to the results,paired with drones and machine learning,tunnel inspections become more effective,and data collection and analysis greatly enhanced.This method has potential use cases in infrastructure monitoring and could possibly be used for other structural damage detection tasks in high-dimensional domains.展开更多
This rise in the deployment of lithium-ion batteries in electric cars presents new fire hazards,especially in places such as tunnels where thermal runaway situations are highly dangerous.This work investigates the pro...This rise in the deployment of lithium-ion batteries in electric cars presents new fire hazards,especially in places such as tunnels where thermal runaway situations are highly dangerous.This work investigates the propagation of thermal runaway in lithium-ion batteries within tunnels,including smoke flow,toxic gas diffusion and heat distribution under various ventilation conditions and tunnel shapes.Tests with 18650 lithium-ion cells were carried out on tunnels with gradients(0°,2°,and 5°),followed by CFD simulations of the results.We measured smoke spread,temperature,and toxic gas concentrations(CO,HF,CO_(2))at airflow rates from 0.5 to 3 m/s.The findings indicated that tunnel slope and ventilation rates had a direct influence on smoke content,gas content and evacuation probability,and that sloping tunnels held more smoke at the ends.These results underscore the need for tailored ventilation to facilitate egress and avoid exposure to toxic gases.This work can inform better fire-safety practices in tunnels as electric vehicles continue to become more common.展开更多
文摘The purpose of this thesis is to use drones and machine learning algorithms for automating crack detection in tunnel systems.With the high resolution RGB cameras and LiDAR sensor in drones,you get the imagery and structural data required to inspect tunnels.The images are then fed through CNNs together with SVMs for detecting and classification cracks in concrete and other surfaces.With this automated mechanism,the process will no longer need manual effort,and the inspection will be more precise and safer.The study shows the efficiency of this hybrid approach,which has 92%detection rate,much better than traditional inspection.And it is also very good at reducing false positives,and produces more trustworthy results.Crack severity is sorted into hairline,medium and deep cracks to make the process of maintenance and repairs easier.According to the results,paired with drones and machine learning,tunnel inspections become more effective,and data collection and analysis greatly enhanced.This method has potential use cases in infrastructure monitoring and could possibly be used for other structural damage detection tasks in high-dimensional domains.
基金supported in part by (i) National Natural Science Foundation of China(NSFC), Nos. 70671100, 71072029, and Beijing Philosophy and Social Science, Research Center for Beijing Transportation Development for J.L. Zhang(ii) NSFC Research Fund Nos. 70971069 and 70772052, and the Fok Ying-Tong Education Foundation of China No. 121078, for Y.J. Li
文摘This rise in the deployment of lithium-ion batteries in electric cars presents new fire hazards,especially in places such as tunnels where thermal runaway situations are highly dangerous.This work investigates the propagation of thermal runaway in lithium-ion batteries within tunnels,including smoke flow,toxic gas diffusion and heat distribution under various ventilation conditions and tunnel shapes.Tests with 18650 lithium-ion cells were carried out on tunnels with gradients(0°,2°,and 5°),followed by CFD simulations of the results.We measured smoke spread,temperature,and toxic gas concentrations(CO,HF,CO_(2))at airflow rates from 0.5 to 3 m/s.The findings indicated that tunnel slope and ventilation rates had a direct influence on smoke content,gas content and evacuation probability,and that sloping tunnels held more smoke at the ends.These results underscore the need for tailored ventilation to facilitate egress and avoid exposure to toxic gases.This work can inform better fire-safety practices in tunnels as electric vehicles continue to become more common.
