Modelo matemático para apoio à gestão da logística de empregados de plataformas offshore de exploração de petróleo

• Ano de defesa: 2013
• Autor(a) principal: Machado, André Manhães
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso aberto
• Idioma: por
• Instituição de defesa: Universidade Federal do Espírito Santo; BR; Mestrado Profissional em Gestão Pública; Centro de Ciências Jurídicas e Econômicas; UFES; Programa de Pós-Graduação em Gestão Pública
• Palavras-chave em Português: Oil logistics; Capacitated helicopter routing problem; Dial-a-ride problem; Logística do petróleo; Logística - Transporte - Empregados; Plataformas de perfuração; Helicópteros; Administração Pública; 35
• Link de acesso: http://repositorio.ufes.br/handle/10/2475

Oil is the main energy source of contemporary world; it is basic inputs of various economic sectors. With the discovery of Brazil pre-salt, there is an opportunity to become one of the largest oil producers. However, to achieve her own goals, Brazil must overcome several challenges, including the problem of transporting employees to operate offshore platforms 300km distant away from the Brazilian coast. Problems related to displacement of employees by helicopters are usually treated as Capacitated Helicopter Routing Problem (CHRP). Based on source and destination restrictions of each client, the number of vehicles, capacity and helicopter flight constraints, this type of problem proposes to minimize the cost of renting helicopters and the total cost of flown kilometers. This dissertation proposes a model of Mixed Integer Linear Programming (MILP) for the helicopters routing problem based on a Dial-a-Ride Problem (DARP). Besides the presented model, we presented two approaches to implementing the model in an exact way: i) non-clustered approach, in which requests that have the same origin and destination are equal modeled as separate requests; and ii) clustered approach, in which requests that have the same origins and destinations are clumped together in a new single request. The mathematical model was implemented in software CPLEX and results showed that instances with up to 25 requests can be resolved in the clustered approach.