Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Cu...Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Currentmanual crack inspection methods are time-consuming and labor-intensive, and most segmentation methods cannot detect cracks at the pixel level. This paper proposes an intelligent segmentation and measurement model basedon the modified Mask R-CNN algorithm to automatically and accurately detect asphalt road cracks. The modelproposed in this paper mainly includes a convolutional neural network (CNN), an optimized region proposalnetwork (RPN), a region of interest (RoI) Align layer, a candidate area classification network and a Mask branch offully convolutional network (FCN). The ratio and size of anchors in the RPN are adjusted to improve the accuracyand efficiency of segmentation. Soft non-maximum suppression (Soft-NMS) algorithm is developed to improvethe segmentation accuracy. A dataset including 8,689 images (512× 512 pixels) of asphalt cracks is established andthe road crack is manually marked. Transfer learning is used to initialize the model parameters in the trainingprocess. To optimize the model training parameters, multiple comparison experiments are performed, and the testresults show that the mean average precision (mAP) value and F1-score of the optimal trained model are 0.952 and0.949. Subsequently, the robustness verification test and comparative test of the trained model are conducted andthe topological features of the crack are extracted. Then, the damage area, length and average width of the crackare measured automatically and accurately at pixel level. More importantly, this paper develops an automatic crackdetection platform for asphalt roads to automatically extract the number, area, length and average width of cracks,which can significantly improve the crack detection efficiency for the road maintenance industry.展开更多
Road constructing in Ethiopia is increasingly in demand to meet its medium and long term development programs.Most internal roads of Oromia city/town are cobblestone and gravel.Some portions along the alignment propos...Road constructing in Ethiopia is increasingly in demand to meet its medium and long term development programs.Most internal roads of Oromia city/town are cobblestone and gravel.Some portions along the alignment proposed and existing roads traversed low resistance of the subgrade that affect the stability of the upper layers of cobblestones.Structural failure is observed on cobblestone roads,and it would be constructed with good quality or low quality of materials.Nekemte Cobblestones Projects have been started in 2014 widely which were filled in most areas today as we observed that needs to be addressed and a corresponding remedial measures must be drawn.A possible counteractive actions had been ordered for every observed destroyed to achieve the standard road situation of the study zone.An evaluation was made use observation,interviews,laboratory test and field test to govern an appropriateness of cobblestones.The lie beneath soil used for bottom layers of road structure based on standard of Ethiopian Road Authority(ERA)low volume road standards.Therefore,result from the field test and laboratory test shown,causes of cobblestone road failures of Nekemte street segment were mostly because of the construction steps/sequence,quality of materials,road construction time,absence of appropriate design,quality supervisor,absences of drainage structures,lack of highly compaction,lack of accurately fill fine aggregate and suddenly high loads vehicle applied on cobblestone road.展开更多
Biodiesel has generated increased interest recently as an alternative to petroleum-derived diesel. Due to its high oxygen content, biodiesel typically burns more completely than petroleum diesel, and thus has lower em...Biodiesel has generated increased interest recently as an alternative to petroleum-derived diesel. Due to its high oxygen content, biodiesel typically burns more completely than petroleum diesel, and thus has lower emissions of hydrocarbons (HC), carbon monoxide (CO), and particulate matter (PM). However, biodiesel may increase or decrease nitrogen oxide (NOx) and carbon dioxide (CO2) emissions, depending on biodiesel feedstock, engine type, and test cycle. The purpose of this study was to compare emissions from 20% blends of biodiesel made from 4 feedstocks (soybean oil, canola oil, waste cooking oil, and animal fat) with emissions from ultra low sulfur diesel (ULSD). Emissions of NOx and CO2 were made under real-world driving conditions using a Horiba On-Board Measurement System OBS-1300 on a highway route and arterial route;emissions of NOx, CO2, HC, CO, and PM were measured in a controlled setting using a chassis dynamometer with Urban Dynamometer Drive Schedule. Dynamometer test results showed statistically significant lower emissions of HC, CO, and PM from all B20 blends compared to ULSD. For CO2, both on-road testing (arterial, highway, and idling) and dynamometer testing showed no statistically significant difference in emissions among the B20 blends and ULSD. For NOx, dynamometer testing showed only B20 from soybean oil to have statistically significant higher emissions. This is generally consistent with the on-road testing, which showed no statistically significant difference in NOx emissions between ULSD and the B20 blends.展开更多
基金This research was funded by the National Key Research and Development Program of China(No.2017YFC1501204)the National Natural Science Foundation of China(No.51678536)+4 种基金the Guangdong Innovative and Entrepreneurial Research Team Program(2016ZT06N340)the Program for Science and Technology Innovation Talents in Universities of Henan Province(Grant No.19HASTIT043)the Outstanding Young Talent Research Fund of Zhengzhou University(1621323001)the Program for Innovative Research Team(in Science and Technology)in University of Henan Province(18IRTSTHN007)the Research on NonDestructive Testing(NDT)and Rapid Evaluation Technology for Grouting Quality of Prestressed Ducts(Contract No.HG-GCKY-01-002).The authors would like to thank for these financial supports.
文摘Nowadays, asphalt road has dominated highways around the world. Among various defects of asphalt road, crackshave been paid more attention, since cracks often cause major engineering and personnel safety incidents. Currentmanual crack inspection methods are time-consuming and labor-intensive, and most segmentation methods cannot detect cracks at the pixel level. This paper proposes an intelligent segmentation and measurement model basedon the modified Mask R-CNN algorithm to automatically and accurately detect asphalt road cracks. The modelproposed in this paper mainly includes a convolutional neural network (CNN), an optimized region proposalnetwork (RPN), a region of interest (RoI) Align layer, a candidate area classification network and a Mask branch offully convolutional network (FCN). The ratio and size of anchors in the RPN are adjusted to improve the accuracyand efficiency of segmentation. Soft non-maximum suppression (Soft-NMS) algorithm is developed to improvethe segmentation accuracy. A dataset including 8,689 images (512× 512 pixels) of asphalt cracks is established andthe road crack is manually marked. Transfer learning is used to initialize the model parameters in the trainingprocess. To optimize the model training parameters, multiple comparison experiments are performed, and the testresults show that the mean average precision (mAP) value and F1-score of the optimal trained model are 0.952 and0.949. Subsequently, the robustness verification test and comparative test of the trained model are conducted andthe topological features of the crack are extracted. Then, the damage area, length and average width of the crackare measured automatically and accurately at pixel level. More importantly, this paper develops an automatic crackdetection platform for asphalt roads to automatically extract the number, area, length and average width of cracks,which can significantly improve the crack detection efficiency for the road maintenance industry.
文摘Road constructing in Ethiopia is increasingly in demand to meet its medium and long term development programs.Most internal roads of Oromia city/town are cobblestone and gravel.Some portions along the alignment proposed and existing roads traversed low resistance of the subgrade that affect the stability of the upper layers of cobblestones.Structural failure is observed on cobblestone roads,and it would be constructed with good quality or low quality of materials.Nekemte Cobblestones Projects have been started in 2014 widely which were filled in most areas today as we observed that needs to be addressed and a corresponding remedial measures must be drawn.A possible counteractive actions had been ordered for every observed destroyed to achieve the standard road situation of the study zone.An evaluation was made use observation,interviews,laboratory test and field test to govern an appropriateness of cobblestones.The lie beneath soil used for bottom layers of road structure based on standard of Ethiopian Road Authority(ERA)low volume road standards.Therefore,result from the field test and laboratory test shown,causes of cobblestone road failures of Nekemte street segment were mostly because of the construction steps/sequence,quality of materials,road construction time,absence of appropriate design,quality supervisor,absences of drainage structures,lack of highly compaction,lack of accurately fill fine aggregate and suddenly high loads vehicle applied on cobblestone road.
文摘Biodiesel has generated increased interest recently as an alternative to petroleum-derived diesel. Due to its high oxygen content, biodiesel typically burns more completely than petroleum diesel, and thus has lower emissions of hydrocarbons (HC), carbon monoxide (CO), and particulate matter (PM). However, biodiesel may increase or decrease nitrogen oxide (NOx) and carbon dioxide (CO2) emissions, depending on biodiesel feedstock, engine type, and test cycle. The purpose of this study was to compare emissions from 20% blends of biodiesel made from 4 feedstocks (soybean oil, canola oil, waste cooking oil, and animal fat) with emissions from ultra low sulfur diesel (ULSD). Emissions of NOx and CO2 were made under real-world driving conditions using a Horiba On-Board Measurement System OBS-1300 on a highway route and arterial route;emissions of NOx, CO2, HC, CO, and PM were measured in a controlled setting using a chassis dynamometer with Urban Dynamometer Drive Schedule. Dynamometer test results showed statistically significant lower emissions of HC, CO, and PM from all B20 blends compared to ULSD. For CO2, both on-road testing (arterial, highway, and idling) and dynamometer testing showed no statistically significant difference in emissions among the B20 blends and ULSD. For NOx, dynamometer testing showed only B20 from soybean oil to have statistically significant higher emissions. This is generally consistent with the on-road testing, which showed no statistically significant difference in NOx emissions between ULSD and the B20 blends.
