Search

Made available in DSpace on 2020-12-10T23:58:44Z (GMT). No. of bitstreams: 0 Previous issue date: 2019-09-01 Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq) The objective of this study is to discuss the main constraints in classifying the severity of road accidents using Artificial Neural Networks (ANN). To achieve this, ANN modelling with Multiple Layers Perceptron (MPL) was used. This method is recommended for treating non-linear problems, whose distributions are not normal, which is the case for road accidents. Variables associated with the characteristics of accidents, road infrastructure and environmental conditions were used, with the objective of identifying the influence of these factors in the accident severity. The results indicated that ANN modelling with MPL presents a potential association among the parameters related to road accidents. However, the results are limited, since the classification process provides a low rate of accuracy for accidents with victims. Such accidents correspond to less frequent observations in the database, meaning that the data is less represented, and the database becomes unbalanced. Thus, for further research studies, the use of ANN with MPL associated with data balancing methods is suggested, in order to obtain the best data fit to the model and more consistent and realistic results. Univ Fed Uberlandia, Fac Civil Engn, Uberlandia, MG, Brazil Univ Sao Paulo, Inst Math & Comp Sci, Sao Paulo, Brazil UNESP Sao Paulo State Univ, Fac Civil Engn, Sao Paulo, Brazil Univ Sao Paulo, Sch Engn Sao Carlos, Dept Transport Engn, Sao Paulo, Brazil UNESP Sao Paulo State Univ, Fac Civil Engn, Sao Paulo, Brazil CNPq: 304683/2015-9

Compósitos de matriz polimérica reciclada reforçados com farinha de madeira podem ser uma alternativa viável para a substituição da madeira e de polímeros virgens em materiais empregados em pisos, batentes de portas, janelas e revestimentos externos. O objetivo desta pesquisa foi determinar alguns parâmetros físicos e mecânicos de compósito com farinha de madeira de Pinus taeda e elliotti e polipropileno reciclado, sem o emprego de compatibilizantes ou aditivos. Os compósitos foram separados em quatro traços, sendo eles: 100% polipropileno, 90% polipropileno com 10% de farinha de madeira, 80% de polipropileno com 20% de farinha de madeira e 70% de polipropileno com 30% de farinha de madeira. Para caracterização do compósito foram utilizadas as normas ASTM D-638-10, ASTM D256-00, ASTM D570-98, ASTM D1238-10 e ASTM G-155-05 e também a análise de superfície por microscopia eletrônica de varredura. Os ensaios de estabilidade dimensional apresentaram resultados satisfatórios. Mesmo o compósito com maior porcentagem de farinha de madeira (30%) apresentou um melhor índice de fluidez de 10,0MFI, sendo considerado compatível com os índices para PP (polipropileno) virgem da norma ASTM D-1238-10. A inclusão de farinha de madeira (FM) proporcionou a obtenção de compósitos com boas características mecânicas que podem ser aplicados na fabricação de diferentes materiais, empregados especificamente em ambientes externos. Recycled polymer matrix composites reinforced with wood flour can be a viable alternative for the replace-ment of wood and virgin polymers in materials used in floors, door frames, windows and external cladding. The objective of this research was to determine some physical and mechanical parameters of composite made with Pinus taeda and elliottii wood flour (WF) and recycled polypropylene (PP), without the use of compatibilizers or additives. The composites were separated into four traits, namely 100% PP, 90% PP with 10%, WF 80% PP with 20% WF and 70 % PP with 30% WF. The characterization of the composite followed the standards ASTM D-638-10, ASTM D256-00, ASTM D570 -98, ASTM D1238 -10 and ASTM G 155-05, it was also employed the surface analysis by scanning electron microscopy. The dimensional stability tests showed satisfactory results. Even the composite with a higher percentage of wood flour (30%) had a flow index of 10 MFI, considered compatible with that observed for PP (polypropylene) virgin by standard ASTM D 1238-10. The inclusion of wood flour (FM) afforded composites with good mechanical characteristics which can be applied in manufacture of different materials, specifically employed outdoors.