No abstract

No abstract

With cutting edge deep learning breakthrough, numerous innovations in many fields including civil engineering are stimulated. However, a fundamental issue that civil engineering research community currently facing is lack of a publicly available, free, quality-controlled and human-annotated large dataset that supports and drives civil engineering deep learning research and applications on such as intelligent transportation including connected vehicle, structural health monitoring, and bridge inspection. This paper is a general discussion about demanding needs and construction of a long-anticipated dataset for researchers and engineers in civil engineering and beyond for providing critical training, testing and benchmarking data. The establishment of such a free dataset will remove a major hurdle and boost deep learning research in civil engineering and we hope this work will urge researchers, engineers, government agencies and even computer scientists to work together to start building such datasets. A framework has been developed for the proposed database. Also, some pilot study databases were developed for concrete crack detection, pavement crack detection using normal and infrared thermography, as well as pedestrian and bicyclist detection. A convolution neural network model called Faster RCNN was deployed to check the detection accuracy and a 98% detection accuracy of the proposed datasets was obtained.

Graphene produced by different methods can present varying physicochemical properties and quality, resulting in a wide range of applications. The implementation of a novel method to synthesize graphene requires characterizations to determine the relevant physicochemical and functional properties for its tailored application. We present a novel method for multilayer graphene synthesis using atmospheric carbon dioxide with characterization. Synthesis begins with carbon dioxide sequestered from air by monoethanolamine dissolution and released into an enclosed vessel. Magnesium is ignited in the presence of the concentrated carbon dioxide, resulting in the formation of graphene flakes. These flakes are separated and enhanced by washing with hydrochloric acid and exfoliation by ammonium sulfate, which is then cycled through a tumble blender and filtrated. Raman spectroscopic characterization, FTIR spectroscopic characterization, XPS spectroscopic characterization, SEM imaging, and TEM imaging indicated that the graphene has fifteen layers with some remnant oxygen-possessing and nitrogen-possessing functional groups. The multilayer graphene flake possessed particle sizes ranging from 2 µm to 80 µm in diameter. BET analysis measured the surface area of the multilayer graphene particles as 330 m2/g, and the pore size distribution indicated about 51% of the pores as having diameters from 0.8 nm to 5 nm. This study demonstrates a novel and scalable method to synthesize multilayer graphene using CO2 from ambient air at 1 g/kWh electricity, potentially allowing for multilayer graphene production by the ton. The approach creates opportunities to synthesize multilayer graphene particles with defined properties through a careful control of the synthesis parameters for tailored applications.

No abstract