Abstract of Thesis presented at COPPE/UFRJ as a partial fulfillment of the requirements for the degree of Master of Science (M.Sc.)

Neuro-Fuzzy Mathematical Model for a Sustainable Construction Subsidize Assessment: The Maglev-Cobra Case

Eloilton Soares Pereira de Souza

March/2016

Advisors:

Marcelo Prado Sucena Richard Magdalena Stephan

Department:

Eletrical Engineering

      The construction sector is associated with significant environmental impacts, and major consumer of raw materials and energy, and generate a lot of pollution. It is therefore essential to head towards sustainable construction. The environmental character requirements for buildings led to the creation of Environmental Performance Works Certification Systems. In the evaluation process of the buildings, there are attributes, mostly with subjectivity characteristics and where the experience of decision makers is quite significant. In this scenario, this work has as main result the development of a mathematical model for obtaining a Sustainability Index of Construction. The proposed index is obtained from the integration of environmental indicators associated with the various construction activities. This integration is achieved employing Fuzzy logic variables that can deal with both qualitative and quantitative nature and from an Artificial Neural Network architecture check adding of an intermediate layer to the next, sets of parameters to reach the desired level. This index will help actors (planners, designers, builders, users and / or operators) in the implementation of the principles of sustainable development in the construction and obtaining the environmental certification process. Model validation will be a case study: The MagLev-Cobra project (COPPE / UFRJ / LASUP).