Modeling maintenance service contracts of a multi-equipment and two-class priority generalized renewal process

• Autor(a) principal: SANTANA, João Mateus Marques de
• Data de Publicação: 2018
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Institucional da UFPE
• Texto Completo: https://repositorio.ufpe.br/handle/123456789/30393
• topic: Engenharia de Produção; Contratos de serviços de manutenção; Jogo de Stackelberg; Processo de renovação generalizado; Simulação de eventos discretos

Due to increasing equipment technology, maintenance activities for complex devices require considerable training, resources, and spare parts for adequate execution. Also, manufacturers often adopt protectionist actions, such as limiting information about maintenance actions, and not providing spare parts to the market. In this context, performing maintenance actions in-house has become costly and inefficient, thus organizations resort to hiring external maintenance services, such as independent service providers or the manufacturer itself. This situation leads to the interaction between different agents; particularly, between service provider and customer (equipment owner). In this work, a model for maintenance service contracts is developed based on a Stackelberg game formulation, considering the interaction between manufacturer, which acts as service provider, and customers, who decide whether to buy a device and which kind of service to hire. Customers are divided into two distinct classes: class 1 is composed by large organizations, which prefer higher equipment availability over cost; class 2 is formed by small organizations, which prefer to pay lower prices for services, even if equipment availability is compromised. Equipment failure-repair behavior follows a generalized renewal process and, since there are multiple devices, each bought by a different customer, a queue system is formed. A discrete event simulation approach is proposed for the solution of the model, overcoming limitations imposed by analytical methods due to model complexity. An application example is presented, along with sensitivity analysis over several of the model’s parameters, with the objective of better understanding model behavior.