Previsão de demanda, classificação multicritério e otimização no planejamento de peças sobressalentes na indústria mineral

Detalhes bibliográficos
Ano de defesa: 2020
Autor(a) principal: Leandro Reis Muniz
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Tese
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Federal de Minas Gerais
Brasil
ENG - DEPARTAMENTO DE ENGENHARIA PRODUÇÃO
Programa de Pós-Graduação em Engenharia de Produção
UFMG
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
AHP
Link de acesso: http://hdl.handle.net/1843/34101
Resumo: This work presents a methodology for managing spare parts in the normal cycle of operation. It presents a literature review, studies forecasting models and proposes combined models. Subsequently, it presents a methodology combined by qualitative and quantitative methods of four phases to assist in decision making in the monthly spare parts planning cycles. It answers the fundamental question of which spare parts to stock and in what quantities. The first phase consists of the selection of criteria using the Cutoff Method, subcriteria and delimitation of categories by the Vital, Essential and Desirable Method (VED). The second uses Hierarchical Process Analysis (AHP) and the Botton-up Method to calculate the total criticality of each item. The third represents the forecast model that generates the values of the optimization model variable. Finally, the fourth phase consists of a biobjective optimization model, based on price and criticality that can perform a single iteration or several by the p-epsilon method and construction of the Pareto Optimal Curve based on forecasts and monthly reviews of balances available for storage of the items. The model is supported by heuristics to prevent unavailability and reduce stockouts. The developed approach evaluates spare parts with real data from 9,263 items from a mining company. As a result, there is better support for the decision during the planning cycles and adequate control of the fixed assets in stock. The scientific contribution consists of the qualitative and quantitative multicriteria model in the management of spare parts prediction with and without lead time, of biobjective optimization models and heuristic methods applied to real data from the mineral industry.